paper-code-audit
Warn
Audited by Snyk on May 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly directs the agent to "compare a paper's claims against its public codebase" via the /audit workflow, which requires fetching and interpreting public papers and third-party code repositories (untrusted, user-generated content) that will directly influence audit decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata