global-agent-guardrails
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily instructional, providing a manual for users or agents to set up local shell command guardrails. It references local configuration files and a shared script (~/.agents/hooks/deny-dangerous.sh) to validate commands against a denylist.
- [SAFE]: The shell commands provided are for checking the status of local files or testing regex patterns (e.g., using python3 to compile lines from a local text file). These do not involve network operations or privilege escalation.
- [SAFE]: The skill explicitly advises against executing dangerous actions, such as dumping keychains or exporting GPG keys, and correctly identifies that regex-based guards can be bypassed by sophisticated obfuscation.
Audit Metadata