enhance-hooks
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection vulnerability surface detected. The skill ingests data from external hook files and configuration settings which could contain instructions intended to influence the agent's behavior during analysis.
- Ingestion points: The skill reads hook scripts (.sh, .md, .json) and configuration files such as ~/.claude/settings.json and project-specific settings.
- Boundary markers: Absent. There are no explicit delimiters or instructions provided to the agent to treat the ingested file content as untrusted data.
- Capability inventory: The skill has the capability to read files from the system and write files (via the --fix flag).
- Sanitization: No specific sanitization or validation logic is defined for the content extracted from audited files.
Audit Metadata