done-done
Warn
Audited by Snyk on Oct 26, 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). The skill instructs the agent to lint external pull request URLs (
done-done lint <PR URL | report file> <evidence folder>), which ingests outsider-authored PR text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata