hook-development
Warn
Audited by Snyk on Aug 19, 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). SKILL.md describes hook events (UserPromptSubmit/PreToolUse/etc.) where the hook’s prompt template can include untrusted runtime fields like $USER_PROMPT and $TOOL_INPUT, meaning outsider-authored free text can reach an LLM-based prompt hook without any selection step.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata