create-hook
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes source code files, creating a surface for indirect prompt injection from untrusted file content. 1. Ingestion points: The skill reads target file contents as defined in Step 1. 2. Boundary markers: No delimiters or instructions to ignore embedded commands are present in the instructions. 3. Capability inventory: The agent is permitted to write to the hooks/ directory and modify existing component files. 4. Sanitization: No sanitization or validation logic is specified for the ingested content. Note: This risk is mitigated by the mandatory human review requirement in Step 5.
Audit Metadata