tk-engineering
Warn
Audited by Snyk on Nov 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow reads the user's own diffs, commit lists, and caller-supplied reported symptoms (diagnosis.md, review-protocol.md), and these may originate from external PRs or bug reports, but the skill names no monitored outsider feed and the agent must select or receive that material rather than having it pushed into a queue, so I'm scoring it low under the recall-first override.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata