Loading...
Loading...
Found 7 Skills
Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.
Scan agent skills for security issues. Use when asked to "scan a skill", "audit a skill", "review skill security", "check skill for injection", "validate SKILL.md", or assess whether an agent skill is safe to install. Checks for prompt injection, malicious scripts, excessive permissions, secret exposure, and supply chain risks.
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations.
Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text from untrusted sources.
Comprehensive security and safety evaluation system for agent skills (.skill files). Use when users provide GitHub URLs, website links, or .skill files for download and request security assessment, safety evaluation, or ask "is this skill safe to use." Evaluates prompt injection risks, malicious code patterns, hidden instructions, data exfiltration attempts, and provides actionable recommendations with risk scoring.
Implements content safety filters with PII redaction, policy constraints, prompt injection detection, and safe refusal templates. Use when adding "content moderation", "safety filters", "PII protection", or "guardrails".
Use this agent when working with prompt injection detection integration tests, including running tests, debugging failures, or adding new test samples.