security-audit

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill explicitly queries public third-party APIs (e.g., GitHub, HuggingFace, LinkedIn, Webex via the curl checks in Step 2) and enumerates/reads repository CLAUDE.md files (Steps 4 and 7), causing the agent to ingest untrusted, user-generated content that can influence validation logic and subsequent actions.