calypso-security-alerts
Pass
Audited by Gen Agent Trust Hub on Jul 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is an advisory tool that triages repository security alerts. It incorporates specific safety instructions to treat external metadata and files as untrusted data, which effectively mitigates the risk of indirect prompt injection.
- [SAFE]: The agent is explicitly restricted from executing shell commands, instead providing recommended commands for a human operator to run after review, which maintains a safe human-in-the-loop security posture.
Audit Metadata