critique
Warn
Audited by Snyk on Aug 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). Outsider-authored free text is written into a temp file and then ingested by the required runtime workflow when it runs Codex read-only on the contents of
/tmp/critique-proposal.md(including any user-provided “Extra focus”), so the LLM reads untrusted text directly before evaluation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata