flake
Warn
Audited by Snyk on Jul 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: 0.85). SKILL.md instructs the agent to fetch and read GitHub issue bodies and Actions job logs at runtime (e.g.,
gh issue view ... --json bodyandgh api .../logs), which are outsider-authored free text from other contributors/CI runs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata