Loading...
Loading...
Found 21 Skills
Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes. Use when reviewing terraform plan output for Azure resources like Application Gateway, Load Balancer, Firewall, Front Door, NSG, and other resources with Set-type attributes that cause spurious diffs due to internal ordering changes.
Guides authoring, review, optimization, and false-positive debugging of YARA-X detection rules for malware identification across PE, script, npm, Office, Chrome extensions (crx module), and Android DEX (dex module). Covers string and atom quality, condition short-circuiting, legacy YARA migration, yarGen/FLOSS workflows, goodware validation, and production deployment—not full malware reverse engineering, network IDS (Suricata/Snort), or memory forensics (Volatility). Use when the user asks to write YARA rule, YARA-X, yr check, yr scan, false positive YARA, yarGen, malware detection rule, crx module, dex module, optimize YARA performance, or migrate legacy YARA.
Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions. Use after running VLM evaluation when you have a predictions JSON and need to identify failure cases for DEFT root cause analysis on a binary-classification VLM workflow.
Run a targeted local React Doctor Evals loop against an uncommitted rule change. Use after focused rule tests pass, while inspecting real open-source hits, or when rule-validate needs local false-positive evidence before pull request parity.
Define a precise React Doctor rule contract before implementation. Use when validating a rule idea, collecting official or open-source evidence, identifying false-positive traps, choosing detector precision, or setting first-version boundaries.
Hunt Local File Inclusion (LFI), Remote File Inclusion (RFI), and Path Traversal — /etc/passwd read, log poisoning → RCE, PHP filter-chain RCE (no upload needed), php:// / data:// / zip:// / phar:// wrappers, RFI via allow_url_include, directory traversal read/write/delete. Covers OOB/blind LFI confirmation and false-positive discipline. Use when hunting file-include or path-traversal bugs on any target.
Comprehensive vulnerability assessment and penetration testing skill leveraging Secator, NetExec, Metasploit, and raw Python for advanced exploitation chaining across Linux, Windows, Unix, macOS systems, network devices (switches, routers, firewalls), protocols, webapps and APIs (REST, GraphQL, gRPC). Uses OSSTMM and OWASP standards. Supports blackbox, greybox, and whitebox pentests with false-positive resistance, verified exploit confirmation, detailed step-by-step remediation, and full documentation. Use when performing security assessments, penetration tests, vulnerability scans, exploit validation, network enumeration, or security auditing.
Analyze CVE vulnerabilities in Java and JavaScript components, determine false positives, and provide upgrade recommendations. Use this when users provide a CVE number and affected object, e.g., CVE-2024-38816 and spring-webmvc-5.3.39.jar. Supports false positive analysis, compatibility risk assessment, and standard report generation.
Evaluate verified findings from merge-ready, Greptile, pull-request, CI, security, billing, and other code reviews, then promote durable review gaps into the version-controlled .greptile configuration. Use when a review uncovers a recurring or high-risk repository invariant that Greptile does not capture, when Greptile repeatedly produces a false positive, or when asked to audit or update OpenSEO's Greptile rules and context.
Scan the codebase for potential secret leaks including API keys, tokens, passwords, hardcoded project IDs, and sensitive identifiers. Use when the user says "check for secrets", "scan for leaks", "security check", or before committing sensitive changes.
Independently reviews findings and filters out false positives. Use when consolidated findings need validation against the actual source code. Don't use for reproducing crashes or patching code.
Fuzz React Doctor rules for crashes, slowness, false positives, and mutation-sensitive diagnostics with @react-doctor/fuzz. Use after rule tests pass, when investigating a fuzz finding, or whenever an eval, review, or user report confirms a new false positive.