bug-report
Warn
Audited by Snyk on Jul 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). SKILL.md’s required workflow in Analyze/Verify/Close modes reads existing markdown files from the repository (e.g.,
production/qa/bugs/[BUG-ID].mdand user-specified target files), which can contain outsider-authored free text such as issue/PR/wiki/discussion content authored by others; that file body is then ingested into the agent’s LLM context for analysis/verification/closure.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata