cc-hooks
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill installs and executes shell scripts as Claude Code hooks (PreToolUse, PostToolUse, etc.) to validate and potentially block tool calls. These scripts utilize standard command-line tools such as jq, grep, sed, awk, and perl to analyze tool inputs against defined policies.
- [DATA_EXFILTRATION]: The skill implements a telemetry system that logs guard activations to a local file (~/.agents/ao/guardrail-telemetry.jsonl). The system is designed with privacy in mind, using SHA-256 hashing for file paths and avoiding the capture of raw command content.
- [EXTERNAL_DOWNLOADS]: The documentation provides instructions for installing external utilities like 'dcg' and 'rch' via package managers, but the skill's own installation and execution scripts do not automatically download or execute remote code.
Audit Metadata