gate-info-risk

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

gate-info-risk

General Rules

通用规则

⚠️ STOP — You MUST read and strictly follow the shared runtime rules before proceeding. Do NOT select or call any tool until all rules are read. These rules have the highest priority. → Read gate-runtime-rules.md → Also read info-news-runtime-rules.md for gate-info and gate-news shared rules.

Only call MCP tools explicitly listed in this skill. Tools not documented here must NOT be called, even if they exist in the MCP server.

⚠️ 停止操作——在继续之前，您必须阅读并严格遵守共享运行时规则。在未阅读所有规则之前，请勿选择或调用任何工具。这些规则具有最高优先级。 → 阅读gate-runtime-rules.md → 同时阅读info-news-runtime-rules.md以了解gate-info和gate-news的共享规则。

仅调用本Skill中明确列出的MCP工具。即使MCP服务器中存在未在此处记录的工具，也不得调用。

CLI and playbook contract

CLI与剧本约定

Legacy commands MUST exist under

gate-cli v0.5.2

. When

shortcuts_enabled

(

>= 0.7.6

token_risk

may use

info +token-risk

per playbook

shortcut

; fall back to

check-token-security

on failure or older CLI. This skill does NOT call

check-address-risk

+address-tracker

for

address_risk

Call
```
gate-cli info …
```
/
```
gate-cli news …
```
only as listed in playbooks/gate-info-risk.yaml. When preflight
```
route
```
is
```
CLI
```
, do not call Gate MCP tools from this skill.
Missing data NEVER counts as "low risk". When the primary command for a chosen playbook is unavailable, the verdict is UNABLE_TO_ASSESS (scope limited; localized labels may appear in the user report) plus an explicit retry hint.
Always pass
```
--format json
```
. Required slots (
```
token
```
+
```
chain
```
,
```
address
```
+
```
chain
```
,
```
symbol
```
) must be present; if ambiguous, ask the user.
The report is safety-first: the verdict line comes BEFORE evidence, and high-severity items are always surfaced before medium or low.
No buy / sell advice. No price predictions. Use verdict bands HIGH / MEDIUM / LOW / UNABLE_TO_ASSESS in this skill’s logic; the final user report may localize those labels. Always include a “what to verify next” list.

旧版命令必须在
```
gate-cli v0.5.2
```
下可用。当
```
shortcuts_enabled
```
（版本≥0.7.6）时，
```
token_risk
```
可根据剧本
```
shortcut
```
使用
```
info +token-risk
```
；若失败或使用旧版CLI，则回退至
```
check-token-security
```
。本Skill不会为
```
address_risk
```
调用
```
check-address-risk
```
或
```
+address-tracker
```
。
仅按照playbooks/gate-info-risk.yaml中的列出方式调用
```
gate-cli info …
```
/
```
gate-cli news …
```
。当预检
```
route
```
为
```
CLI
```
时，请勿从此Skill调用Gate MCP工具。
数据缺失绝不视为“低风险”。当所选剧本的主命令不可用时，结论为UNABLE_TO_ASSESS（范围受限；用户报告中可能显示本地化标签），并附带明确的重试提示。
始终传递
```
--format json
```
。必填槽位（
```
token
```
+
```
chain
```
、
```
address
```
+
```
chain
```
、
```
symbol
```
）必须存在；若存在歧义，请询问用户。
报告以安全优先：结论行位于证据之前，高严重性项始终优先于中低严重性项展示。
不提供买入/卖出建议，不做价格预测。本Skill逻辑中使用结论等级HIGH / MEDIUM / LOW / UNABLE_TO_ASSESS；最终用户报告可能会本地化这些标签。始终包含**“下一步需验证内容”**列表。

Step 0 — Preflight

步骤0 — 预检

Follow the shared contract in skills/_shared/preflight.md verbatim. Summary:

Run

gate-cli preflight --format json

; parse

.route

.status

.user_message

Branch:
```
CLI
```
→ continue;
```
MCP_FALLBACK
```
→ emit
```
__FALLBACK__
```
and halt;
```
BLOCK
```
→ echo
```
user_message
```
and halt.
When
```
status == "ready_with_migration_warning"
```
, Step 3 appends one migrate hint at the very end of the report.
Step 0.5: Set
```
cli_version
```
and
```
shortcuts_enabled
```
per skills/_shared/cli-version-routing.md.

Do NOT run any data-collection command until Step 0 returns

route == "CLI"

严格遵循skills/_shared/preflight.md中的共享约定。摘要：

运行

gate-cli preflight --format json

；解析

.route

、

.status

、

.user_message

。

分支处理：
```
CLI
```
→ 继续；
```
MCP_FALLBACK
```
→ 输出
```
__FALLBACK__
```
并终止；
```
BLOCK
```
→ 回显
```
user_message
```
并终止。
当
```
status == "ready_with_migration_warning"
```
时，步骤3需在报告末尾追加一条迁移提示。
步骤0.5：根据skills/_shared/cli-version-routing.md设置
```
cli_version
```
和
```
shortcuts_enabled
```
。

在步骤0返回

route == "CLI"

之前，请勿运行任何数据收集命令。

Step 1 — Intent routing

步骤1 — 意图路由

Pick exactly one playbook id from playbooks/gate-info-risk.yaml:

Playbook id	When to pick	Required slots
`token_risk`	"is this token safe", "is there a honeypot", "taxes too high", "holder concentration" — subject is a token contract.	`token` , `chain` (the `token` slot accepts ticker OR contract address)
`address_risk`	"is this address safe", "sanctioned / OFAC", "blacklist", "is this wallet risky".	`address` , `chain`
`project_risk`	"compliance or incident risk for this project", "has there been a security incident on {project}", "exchange announcement risk".	`symbol`

从playbooks/gate-info-risk.yaml中选择恰好一个剧本ID：

剧本ID	选择时机	必填槽位
`token_risk`	用户询问“这个代币安全吗”、“是不是蜜罐”、“手续费太高”、“持有者集中度”等——主题为代币合约。	`token` 、 `chain` （ `token` 槽位接受代码或合约地址）
`address_risk`	用户询问“这个地址安全吗”、“是否受制裁/OFAC管控”、“是否在黑名单”、“这个钱包有风险吗”等。	`address` 、 `chain`
`project_risk`	用户询问“这个项目的合规或事件风险”、“{项目}是否发生过安全事件”、“交易所公告风险”等。	`symbol`

Slot extraction rules

槽位提取规则

```
check-token-security
```
takes exactly one of
```
--token
```
or
```
--address
```
— the CLI explicitly rejects passing both (see the CLI error message; mutually exclusive). This skill always uses
```
--token
```
because the flag is polymorphic: it accepts BOTH tickers (
```
USDT
```
) and contract addresses (
```
0xdAC17F...
```
, SPL mints, TRX mints). Agent slot-extraction rule: when the user mentions a contract address for a token-risk query, store that address in the
```
token
```
slot directly — do NOT create a parallel
```
address
```
slot for this playbook. Always pair with
```
--chain
```
.
```
chain
```
canonical form (always send the short id on
```
--chain
```
):
```
eth
```
,
```
bsc
```
,
```
polygon
```
,
```
arb
```
,
```
op
```
,
```
base
```
,
```
avax
```
,
```
solana
```
,
```
tron
```
, ... Accept common long-form aliases from users (
```
ethereum
```
,
```
arbitrum
```
,
```
optimism
```
,
```
avalanche
```
,
```
bnb
```
,
```
matic
```
) and normalize to the short id before calling the CLI. Response
```
.chain
```
echo is endpoint-dependent — sometimes short (
```
eth
```
→
```
eth
```
), sometimes long (
```
arb
```
→
```
arbitrum
```
). Parsers MUST accept both alias forms; see skills/gate-info-risk/references/troubleshooting.md (canonical alias table for input normalization and response parsing).
```
address
```
is a wallet. If the user asks about a token contract but passed an address, confirm which they mean.
```
symbol
```
for
```
project_risk
```
is the listed coin ticker; resolve ambiguous project names before calling
```
news
```
commands.
Missing or ambiguous required slot → STOP, ask the user. Do not guess.

```
check-token-security
```
仅接受
```
--token
```
或
```
--address
```
中的一个——CLI明确拒绝同时传递两者（参见CLI错误信息；互斥）。本Skill始终使用
```
--token
```
，因为该标志具有多态性：它既接受代码（如
```
USDT
```
）也接受合约地址（如
```
0xdAC17F...
```
、SPL铸币地址、TRX铸币地址）。Agent槽位提取规则：当用户在代币风险查询中提及合约地址时，直接将该地址存储在
```
token
```
槽位中——请勿为此剧本创建并行的
```
address
```
槽位。始终与
```
--chain
```
配合使用。
```
chain
```
的标准格式（在
```
--chain
```
参数中始终发送短ID）：
```
eth
```
、
```
bsc
```
、
```
polygon
```
、
```
arb
```
、
```
op
```
、
```
base
```
、
```
avax
```
、
```
solana
```
、
```
tron
```
等。接受用户常用的长别名（如
```
ethereum
```
、
```
arbitrum
```
、
```
optimism
```
、
```
avalanche
```
、
```
bnb
```
、
```
matic
```
），并在调用CLI前将其标准化为短ID。响应中的
```
.chain
```
回显形式取决于端点——有时是短格式（
```
eth
```
→
```
eth
```
），有时是长格式（
```
arb
```
→
```
arbitrum
```
）。解析器必须接受两种别名形式；参见skills/gate-info-risk/references/troubleshooting.md（用于输入标准化和响应解析的标准别名表）。
```
address
```
指钱包地址。如果用户询问代币合约但提供的是地址，请确认用户所指内容。
```
project_risk
```
中的
```
symbol
```
是上市代币的代码；在调用
```
news
```
命令前需解析模糊的项目名称。
缺失或歧义的必填槽位→停止操作，询问用户。请勿猜测。

Cross-skill routing at Step 1

步骤1的跨Skill路由

User signal	Route to
"just give me a general analysis of this coin", no safety framing	`gate-info-research`
"who is this address / what is it doing on-chain" (not risk-first)	`gate-info-web3`
"why did it drop" / "community view on incident"	`gate-news-intel`

用户信号	路由至
“给我这个币的通用分析”，无安全相关表述	`gate-info-research`
“这个地址是什么/它在链上做什么”（非风险优先）	`gate-info-web3`
“为什么暴跌”/“社区对该事件的看法”	`gate-news-intel`

Step 2 — Data collection

步骤2 — 数据收集

All commands use

--format json

. Commands inside the same

parallel_group

run concurrently.

When

shortcuts_enabled

and playbook defines

shortcut

, follow skills/_shared/cli-version-routing.md. Map

+token-risk

output (

risk_level

risk_items

token_identity

) to the same verdict rules as

check-token-security

token_risk
shortcut args: use playbook

args

(

--symbol

) for tickers;

args_when

with

when: contract_address

(

--address

--chain

) for contract-shaped

token

. After shortcut success, still run optional

token_onchain

(

post_shortcut_optional_ids

) — shortcut does not include on-chain holder data.

所有命令均使用

--format json

。同一

parallel_group

内的命令可并发运行。

当

shortcuts_enabled

且剧本定义了

shortcut

时，遵循skills/_shared/cli-version-routing.md。将

+token-risk

的输出（

risk_level

、

risk_items

、

token_identity

）映射为与

check-token-security

相同的结论规则。

token_risk
快捷参数：对代币代码使用剧本

args

（

--symbol

）；对合约格式的

token

使用

args_when

并设置

when: contract_address

（

--address

--chain

）。快捷方式成功后，仍需运行可选的

token_onchain

（

post_shortcut_optional_ids

）——快捷方式不包含链上持有者数据。

2.A

token_risk

2.A

token_risk

Shortcut (>= 0.7.6): resolve args from playbook

shortcut.args

shortcut.args_when

(never default to

--address

for tickers). On native-coin resolution failure, fall back to legacy commands below.

Required (legacy):

gate-cli info compliance check-token-security --token {token} --chain {chain} --scope full

Optional (run in parallel with the above):

gate-cli info coin get-coin-info --query {symbol_or_token} --chain {chain} --scope basic

— project fundamentals for context.

gate-cli info onchain get-token-onchain --token {token} --chain {chain} --scope full

— holder concentration, smart-money flow.

快捷方式（≥0.7.6）：从剧本

shortcut.args

shortcut.args_when

解析参数（代币代码绝不默认使用

--address

）。如果原生代币解析失败，则回退至下方的旧版命令。

必填（旧版）：

gate-cli info compliance check-token-security --token {token} --chain {chain} --scope full

可选（与上述命令并行运行）：

gate-cli info coin get-coin-info --query {symbol_or_token} --chain {chain} --scope basic

—— 项目基本面信息，用于上下文补充。

gate-cli info onchain get-token-onchain --token {token} --chain {chain} --scope full

—— 持有者集中度、聪明资金流向。

2.B

address_risk

2.B

address_risk

Required:

gate-cli info onchain get-address-info --address {address} --chain {chain} --scope basic

— risk labels, tags, scoped balance summary.

Optional:

gate-cli info onchain get-address-transactions --address {address} --chain {chain} --time-range 30d --min-value-usd 100000 --limit 50

— recent large flows; helps flag mixing / exchange hopping.

Scope-limited rule:
gate-cli
v0.5.2 does not expose
info compliance check-address-risk
. If
get-address-info
returns no risk labels or tags, the final verdict MUST be UNABLE_TO_ASSESS (localized in user output) with a note to re-check once the dedicated address-risk command ships.

必填：

gate-cli info onchain get-address-info --address {address} --chain {chain} --scope basic

—— 风险标签、标记、限定范围的余额摘要。

可选：

gate-cli info onchain get-address-transactions --address {address} --chain {chain} --time-range 30d --min-value-usd 100000 --limit 50

—— 近期大额交易流水；有助于标记混币/跨交易所转移行为。

范围受限规则：
gate-cli
v0.5.2未提供
info compliance check-address-risk
。如果
get-address-info
未返回任何风险标签或标记，最终结论必须为UNABLE_TO_ASSESS（在用户输出中本地化），并附带说明，提示用户在专用地址风险命令发布后重新检查。

2.C

project_risk

2.C

project_risk

Required (run in parallel):

gate-cli news feed search-news --coin {symbol} --limit 10 --sort-by importance --time-range 7d

gate-cli news events get-latest-events --coin {symbol} --time-range 7d --limit 20

(server enum is

1h|24h|7d

— use

--start-time

--end-time

unix-ms for longer windows)

Optional:

gate-cli news feed get-exchange-announcements --coin {symbol} --limit 10

— listing / delisting / maintenance / emergency notices.

必填（并行运行）：

gate-cli news feed search-news --coin {symbol} --limit 10 --sort-by importance --time-range 7d

gate-cli news events get-latest-events --coin {symbol} --time-range 7d --limit 20

（服务器枚举值为

1h|24h|7d

——对于更长时间窗口，使用

--start-time

--end-time

Unix时间戳（毫秒））

可选：

gate-cli news feed get-exchange-announcements --coin {symbol} --limit 10

—— 上线/下线/维护/紧急公告。

Failure policy

失败处理策略

Required command failure → abort playbook, surface CLI error verbatim (trim auth), stop. No verdict is emitted.
Optional command failure → mark the corresponding section
```
scope limited
```
in Step 3 and downgrade confidence.
Upstream returns "not found" or empty labels → treat as data gap, NOT as low risk.

必填命令失败→终止剧本，直接显示CLI错误信息（移除认证相关内容），停止操作。不输出结论。
可选命令失败→在步骤3中标记对应部分为
```
范围受限
```
并降低置信度。
上游返回“未找到”或空标签→视为数据缺口，而非低风险。

Step 3 — Synthesis

步骤3 — 综合分析

The report is always 5 sections, in this order:

报告始终包含5个部分，顺序如下：

Report template

报告模板

markdown

undefined

markdown

undefined

Risk assessment — {subject}

风险评估 — {subject}

1. Verdict

1. 结论

Level: {HIGH | MEDIUM | LOW | UNABLE_TO_ASSESS} (you may localize labels in the user-facing report)
Three short sentences: main basis + data coverage + confidence (whether scope-limited)

等级: {HIGH | MEDIUM | LOW | UNABLE_TO_ASSESS}（面向用户的报告中可本地化标签）
三句简短描述：主要依据 + 数据覆盖范围 + 置信度（是否范围受限）

2. Core risk items

2. 核心风险项

Sort strictly HIGH → MEDIUM → LOW. Each item includes:

Risk name + taxonomy:

TECHNICAL_CONTRACT

ADDRESS_COMPLIANCE

PROJECT_LEVEL

Evidence (real JSON paths), e.g.

check-token-security.high_risk_list[?risk_key=="is_honeypot"].risk_value == "1"

check-token-security.data_analysis.top10_percent

get-address-info.risk_labels

Impact + trigger (e.g. “tax rises after holding > 7 days”)

严格按照HIGH → MEDIUM → LOW排序。每个风险项包含：

风险名称 + 分类：

TECHNICAL_CONTRACT

ADDRESS_COMPLIANCE

PROJECT_LEVEL

证据（实际JSON路径），例如

check-token-security.high_risk_list[?risk_key=="is_honeypot"].risk_value == "1"

、

check-token-security.data_analysis.top10_percent

、

get-address-info.risk_labels

影响 + 触发条件（例如“持有超过7天后手续费上涨”）

3. On-chain or compliance context

3. 链上或合规上下文

{Balances / tags / labels / large flows / holder concentration / fundamentals. Sources as hit by playbook:

info onchain get-address-info

info onchain get-address-transactions

info onchain get-token-onchain

info coin get-coin-info

}

{余额/标签/标记/大额交易流水/持有者集中度/基本面信息。来源为剧本调用的工具：

info onchain get-address-info

、

info onchain get-address-transactions

、

info onchain get-token-onchain

、

info coin get-coin-info

}

4. Event context (if any)

4. 事件上下文（如有）

{Last 7–30d news / incidents / announcements from

news feed search-news

news events get-latest-events

news feed get-exchange-announcements

. Separate sourced facts from community speculation (mark “needs confirmation” where needed).}

If the playbook did not call news commands, mark no data; you may suggest

gate-news-intel

for follow-up.

{过去7–30天的新闻/事件/公告，来自

news feed search-news

、

news events get-latest-events

、

news feed get-exchange-announcements

。区分已验证事实与社区猜测（必要时标记“需确认”）。}

如果剧本未调用新闻命令，标记为无数据；可建议用户使用

gate-news-intel

进行后续查询。

5. What to verify next

5. 下一步需验证内容

List concrete next commands to close each gap
If UNABLE_TO_ASSESS, the first bullet must tell the user to re-run
```
check-token-security
```
/
```
get-address-info
```
with the correct
```
{chain}
```
No buy/sell advice; no price targets

undefined

列出具体的后续命令以填补每个数据缺口
如果结论为UNABLE_TO_ASSESS，第一条必须告知用户使用正确的
```
{chain}
```
重新运行
```
check-token-security
```
/
```
get-address-info
```
不提供买入/卖出建议；不给出价格目标

undefined

Verdict rules (applied in section 1)

结论规则（应用于第1部分）

check-token-security

intentionally surfaces two type conventions — agents must not mix them:

Top-level flags (e.g.
```
.is_honeypot
```
,
```
.is_open_source
```
) are JSON booleans (
```
true
```
/
```
false
```
). Compare with
```
== true
```
/
```
== false
```
, NOT with
```
"1"
```
/
```
"0"
```
.

Nested list entries inside

high_risk_list[]

middle_risk_list[]

low_risk_list[]

risky_list[]

attention_list[]

have

.risk_value

as strings (

"0"

"1"

). Compare with

== "1"

or cast via

tonumber

Tax fields (
```
.buy_tax
```
,
```
.sell_tax
```
, nested
```
.tax_analysis.token_tax.{buy_tax,sell_tax,transfer_tax}
```
) are strings (percent without
```
%
```
). Cast with
```
tonumber
```
before numeric comparison.

Percent fields under

.data_analysis

(

.top10_percent

.top100_percent

.dev_holding_percent

.insider_percent

.max_holder_percent

) are strings. Cast before comparing.

Each nested entry has shape

{risk_key, risk_value, risk_level, risk_name, risk_desc}

Signal (real JSON path)	Effect on verdict
`high_risk_list[?risk_key=="is_honeypot"].risk_value == "1"` (equivalently top-level `is_honeypot == true` — top-level is boolean, not string)	HIGH (immediate)
`high_risk_list[?risk_key=="is_high_tax"].risk_value == "1"` OR `tonumber(buy_tax) > 10` OR `tonumber(sell_tax) > 10`	At least HIGH
`middle_risk_list[?risk_key=="owner_change_balance"].risk_value == "1"` (owner can rewrite any holder's balance)	HIGH (immediate)
`middle_risk_list[?risk_key=="can_take_back_ownership"].risk_value == "1"` OR `middle_risk_list[?risk_key=="hidden_owner"].risk_value == "1"` OR `middle_risk_list[?risk_key=="self_destruct"].risk_value == "1"`	HIGH (immediate)
`middle_risk_list[?risk_key=="is_mintable"].risk_value == "1"` OR `middle_risk_list[?risk_key=="is_proxy"].risk_value == "1"` OR `middle_risk_list[?risk_key=="is_blacklisted"].risk_value == "1"`	At least MEDIUM
`high_risk_list[?risk_key=="is_open_source"].risk_value == "0"` (equivalently top-level `is_open_source == false` — boolean at top level)	At least MEDIUM
`tonumber(data_analysis.top10_percent) > 70` (or top-level `top10_percent` ) and no lock-up evidence	At least MEDIUM
`get-address-info.risk_labels` includes `OFAC` / `sanctioned` / `mixer` / `scam` / `exchange-hack-proceeds` / `darknet`	HIGH (immediate)
`get-address-info` returns `risk_labels=[]` AND `tags=[]`	UNABLE_TO_ASSESS (scope limited) — do not downgrade to LOW
`holders.holder_concentration[?label=="No.1-10"].percentage > 0.5` and active large turnover in 7d ( `get-token-onchain` )	Add MEDIUM item
`latest-events` has `event_type == "exploit" / "rug" / "depeg"` and `create_time` ≤ 7d	Add MEDIUM or HIGH (by severity)
All required commands fail	UNABLE_TO_ASSESS + clear retry guidance

Optional summary shortcut:

check-token-security.risk_summary.highest_risk_level

— an aggregate

0–3

severity score from upstream (3 = honeypot-grade). When

highest_risk_level >= 3

without any flagged

risk_key

, still run through the rules above to cite the specific offending field rather than citing

risk_summary

alone.

check-token-security

明确采用两种类型约定——Agent不得混用：

顶层标志（例如
```
.is_honeypot
```
、
```
.is_open_source
```
）为JSON布尔值（
```
true
```
/
```
false
```
）。需与
```
== true
```
/
```
== false
```
比较，而非
```
"1"
```
/
```
"0"
```
。

high_risk_list[]

、

middle_risk_list[]

、

low_risk_list[]

、

risky_list[]

、

attention_list[]

内的嵌套列表项的

.risk_value

为字符串（

"0"

"1"

）。需与

== "1"

比较或通过

tonumber

转换。

手续费字段（
```
.buy_tax
```
、
```
.sell_tax
```
、嵌套的
```
.tax_analysis.token_tax.{buy_tax,sell_tax,transfer_tax}
```
）为字符串（不带
```
%
```
的百分比）。在数值比较前需通过
```
tonumber
```
转换。

.data_analysis

下的百分比字段（

.top10_percent

、

.top100_percent

、

.dev_holding_percent

、

.insider_percent

、

.max_holder_percent

）为字符串。比较前需转换。

每个嵌套项的格式为

{risk_key, risk_value, risk_level, risk_name, risk_desc}

。

信号（实际JSON路径）	对结论的影响
`high_risk_list[?risk_key=="is_honeypot"].risk_value == "1"` （等效于顶层 `is_honeypot == true` ——顶层为布尔值，非字符串）	立即判定为HIGH
`high_risk_list[?risk_key=="is_high_tax"].risk_value == "1"` 或 `tonumber(buy_tax) > 10` 或 `tonumber(sell_tax) > 10`	至少判定为HIGH
`middle_risk_list[?risk_key=="owner_change_balance"].risk_value == "1"` （所有者可修改任意持有者的余额）	立即判定为HIGH
`middle_risk_list[?risk_key=="can_take_back_ownership"].risk_value == "1"` 或 `middle_risk_list[?risk_key=="hidden_owner"].risk_value == "1"` 或 `middle_risk_list[?risk_key=="self_destruct"].risk_value == "1"`	立即判定为HIGH
`middle_risk_list[?risk_key=="is_mintable"].risk_value == "1"` 或 `middle_risk_list[?risk_key=="is_proxy"].risk_value == "1"` 或 `middle_risk_list[?risk_key=="is_blacklisted"].risk_value == "1"`	至少判定为MEDIUM
`high_risk_list[?risk_key=="is_open_source"].risk_value == "0"` （等效于顶层 `is_open_source == false` ——顶层为布尔值）	至少判定为MEDIUM
`tonumber(data_analysis.top10_percent) > 70` （或顶层 `top10_percent` ）且无锁仓证据	至少判定为MEDIUM
`get-address-info.risk_labels` 包含 `OFAC` / `sanctioned` / `mixer` / `scam` / `exchange-hack-proceeds` / `darknet`	立即判定为HIGH
`get-address-info` 返回 `risk_labels=[]` 且 `tags=[]`	判定为UNABLE_TO_ASSESS（范围受限）——不得降级为LOW
`holders.holder_concentration[?label=="No.1-10"].percentage > 0.5` 且7天内有活跃大额交易量（来自 `get-token-onchain` ）	添加MEDIUM风险项
`latest-events` 中存在 `event_type == "exploit" / "rug" / "depeg"` 且 `create_time` ≤ 7天	根据严重性添加MEDIUM或HIGH风险项
所有必填命令失败	判定为UNABLE_TO_ASSESS + 清晰的重试指引

可选的摘要快捷方式：

check-token-security.risk_summary.highest_risk_level

——上游提供的0–3级严重程度总分（3级为蜜罐级）。当

highest_risk_level >= 3

但未标记任何

risk_key

时，仍需通过上述规则找出具体违规字段，而非仅引用

risk_summary

。

Migrate hint (only when Step 0 status was

ready_with_migration_warning

)

迁移提示（仅当步骤0状态为

ready_with_migration_warning

时）

At the end of the report, append verbatim the migration blockquote line from skills/_shared/report-style.md (line starting with

⚙️

and

gate-cli migrate --dry-run

Never gate the verdict on migrate status.

在报告末尾，逐字添加skills/_shared/report-style.md中的迁移引用行（以

⚙️

和

gate-cli migrate --dry-run

开头的行）。

结论不得受迁移状态影响。

Cross-skill routing + Safety rules

跨Skill路由 + 安全规则

Routing

路由

Follow the shared matrix in skills/_shared/routing.md. Risk-skill-specific follow-ups:

Follow-up intent	Target
"full research" / "is it worth following"	`gate-info-research`
"what is this address doing" / "smart money behavior"	`gate-info-web3`
"why it dropped" / "community take on the event"	`gate-news-intel`
User changes chain or token and wants a new assessment	Re-enter the same playbook with new slots; do NOT reuse prior verdict.

遵循skills/_shared/routing.md中的共享矩阵。风险Skill专属的后续路由：

后续意图	目标
“完整研究” / “是否值得关注”	`gate-info-research`
“这个地址在做什么” / “聪明资金行为”	`gate-info-web3`
“为什么暴跌” / “社区对事件的看法”	`gate-news-intel`
用户更改链或代币并需要新评估	使用新槽位重新进入同一剧本；不得复用之前的结论。

Safety rules

安全规则

Follow the shared contract in skills/_shared/report-style.md. Risk-specific hardening:

Never say LOW when a required command failed or when no risk labels / security-check fields were returned; use UNABLE_TO_ASSESS (or localized equivalent).
Keep the three risk taxonomies (
```
TECHNICAL_CONTRACT
```
/
```
ADDRESS_COMPLIANCE
```
/
```
PROJECT_LEVEL
```
) strictly separate in Section 2.
HIGH items MUST appear before any MEDIUM or LOW items in Section 2.
No buy / sell advice. The closest allowed phrasing is “avoid / verify further” (neutral, non-prescriptive).

Cite the exact JSON path for every verdict-driving claim, e.g.

info compliance check-token-security.high_risk_list[?risk_key=="is_honeypot"].risk_value

info compliance check-token-security.data_analysis.top10_percent

— never cite a command-only hand-wave like "from check-token-security".

遵循skills/_shared/report-style.md中的共享约定。风险Skill专属强化规则：

当必填命令失败或未返回任何风险标签/安全检查字段时，绝不说LOW；使用UNABLE_TO_ASSESS（或本地化等效表述）。
在第2部分中严格区分三种风险分类（
```
TECHNICAL_CONTRACT
```
/
```
ADDRESS_COMPLIANCE
```
/
```
PROJECT_LEVEL
```
）。
HIGH风险项必须在第2部分中优先于任何MEDIUM或LOW风险项展示。
不提供买入/卖出建议。允许的最接近表述为“避免/进一步验证”（中立、非指令性）。

为每个驱动结论的声明引用确切的JSON路径，例如

info compliance check-token-security.high_risk_list[?risk_key=="is_honeypot"].risk_value

或

info compliance check-token-security.data_analysis.top10_percent

——绝不仅引用命令名称如“来自check-token-security”。

References

参考资料

File	Load when...
skills/gate-info-risk/references/scenarios.md	Picking a playbook id is not obvious, or the user's prompt looks like Scenarios 4 / 5 (address risk, major-coin ambiguity).
skills/gate-info-risk/references/cli-reference.md	You need the full flag table for `check-token-security` , `get-address-info` , `get-token-onchain` , or the auxiliary news commands.
skills/gate-info-risk/references/troubleshooting.md	A command failed, or `get-address-info` came back with no risk labels (the `check-address-risk` gap).
skills/_shared/preflight.md	Step 0 contract.
skills/_shared/routing.md	Cross-skill routing.
skills/_shared/report-style.md	Safety + reporting rules.
skills/_shared/update-workflow.md	Skill update workflow.

文件	加载时机...
skills/gate-info-risk/references/scenarios.md	剧本ID选择不明确，或用户提示类似场景4/5（地址风险、主流币歧义）时。
skills/gate-info-risk/references/cli-reference.md	需要 `check-token-security` 、 `get-address-info` 、 `get-token-onchain` 或辅助新闻命令的完整标志表时。
skills/gate-info-risk/references/troubleshooting.md	命令失败，或 `get-address-info` 未返回任何风险标签（ `check-address-risk` 功能缺口）时。
skills/_shared/preflight.md	步骤0约定。
skills/_shared/routing.md	跨Skill路由。
skills/_shared/report-style.md	安全+报告规则。
skills/_shared/update-workflow.md	Skill更新流程。

gate-info-risk

Original

Translation

gate-info-risk

gate-info-risk

General Rules

通用规则

CLI and playbook contract

CLI与剧本约定

Step 0 — Preflight

步骤0 — 预检

Step 1 — Intent routing

步骤1 — 意图路由

Slot extraction rules

槽位提取规则

Cross-skill routing at Step 1

步骤1的跨Skill路由

Step 2 — Data collection

步骤2 — 数据收集

2.A token_risk

2.A token_risk

2.B address_risk

2.B address_risk

2.C project_risk

2.C project_risk

Failure policy

失败处理策略

Step 3 — Synthesis

步骤3 — 综合分析

Report template

报告模板

Risk assessment — {subject}

风险评估 — {subject}

1. Verdict

1. 结论

2. Core risk items

2. 核心风险项

3. On-chain or compliance context

3. 链上或合规上下文

4. Event context (if any)

4. 事件上下文（如有）

5. What to verify next

5. 下一步需验证内容

Verdict rules (applied in section 1)

结论规则（应用于第1部分）

Migrate hint (only when Step 0 status was ready_with_migration_warning)

迁移提示（仅当步骤0状态为ready_with_migration_warning时）

Cross-skill routing + Safety rules

跨Skill路由 + 安全规则

Routing

路由

Safety rules

安全规则

References

参考资料

2.A
`token_risk`

2.A
`token_risk`

2.B
`address_risk`

2.B
`address_risk`

2.C
`project_risk`

2.C
`project_risk`

Migrate hint (only when Step 0 status was
`ready_with_migration_warning`
)

迁移提示（仅当步骤0状态为
`ready_with_migration_warning`
时）