claude-code-analyzer
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill runs GitHub discovery (scripts/github-discovery.sh, invoked by scripts/analyze.sh and described in SKILL.md) that searches public GitHub repositories and returns/ingests search results from user-generated public code, which the agent reads and interprets as part of its workflow, exposing it to untrusted third‑party content.
Audit Metadata