performance-review-manager
Warn
Audited by Snyk on Jul 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the LLM context via Step 3/“Gather inputs” when the skill reads peer feedback files from
Q*/employee-name/sources/*-from-*.md, where those files are authored by other reviewers (outsiders) and then synthesized into quotes/summaries for the manager.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata