hook-system
Warn
Audited by Snyk on Aug 22, 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 description defines a hook architecture where operator-configured hooks can intercept
UserPromptSubmit/PreToolUsepayloads (including user-submitted prompt text) and pass/transform it, so an outsider can supply free text that the workflow ingests via the prompt lifecycle.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata