skill-stocktake
Warn
Audited by Snyk on Jul 29, 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’s Phase 2 invokes a subagent that “reads each skill” from the inventoried
~/.gemini/skills/...and{cwd}/.gemini/skills/...paths (first-party local files authored/posted by the user), so it ingests outsider-authored free text via skill file contents at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata