autoplan
Warn
Audited by Snyk on May 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly uses WebSearch and runs Codex with "--enable web_search_cached" and repeatedly instructs "run searches if WebSearch available" (e.g., Phase 0.5 / Codex prompts, DX "Competitive benchmark: run searches"), and even offers to open a public URL (https://garryslist.org/...), so it will fetch and interpret open-web content that could contain untrusted/user-generated instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata