hook-audit

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands such as ls, wc, jq, and git rev-parse to identify hook scripts and count session metric files. These operations are limited to specific local directories and are used for information gathering consistent with the skill's purpose.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) as it processes data from external files that could contain malicious instructions.
  • Ingestion points: Reads metrics data from ~/.claude/hook-metrics/*.json, rules from CLAUDE.md, and history from git log.
  • Boundary markers: None provided in the instructions to separate data from instructions.
  • Capability inventory: The skill can execute shell commands and read files.
  • Sanitization: No input validation or escaping is applied to the contents of the analyzed files.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 09:07 AM
Security Audit — agent-trust-hub — hook-audit