install-hooks

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Bash(chmod:*) to grant execution permissions to scripts stored in the .claude/hooks/ directory, enabling them to run on agent events.
  • [COMMAND_EXECUTION]: It leverages Bash(jq:*) to programmatically update settings.json, allowing for the persistent registration of these hook scripts.
  • [PROMPT_INJECTION]: An indirect prompt injection surface exists through the use of $ARGUMENTS to influence script installation and configuration. 1. Ingestion point: $ARGUMENTS in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Write, Bash(chmod:*), Bash(jq:*) in SKILL.md. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 07:24 PM
Security Audit — agent-trust-hub — install-hooks