llm-attacks-security
Fail
Audited by Snyk on Feb 23, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E006: Malicious code pattern detected in skill scripts.
- Malicious code pattern detected (high risk: 1.00). This content explicitly documents and facilitates offensive LLM attack techniques—prompt injection, jailbreaking, training-data and secret extraction—indicating clear intent to enable abuse and high risk for malicious misuse.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md Data Source explicitly instructs the agent to fetch and use content from the public URL https://raw.githubusercontent.com/gmh5225/awesome-ai-security/refs/heads/main/README.md, meaning the agent will ingest untrusted, user-maintained third‑party content that can influence its workflow and actions.
Audit Metadata