e2e
Warn
Audited by Snyk on Aug 14, 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). Outsider-authored free text is ingested at runtime via the first position of the skill’s
$ARGUMENTS“free-form prompt” (Phase 0/1 →detect-mode.shand then passed asPROMPTcontext into mode flows like create/update/review/rules).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata