pc-safety-guard
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The content of the skill is purely instructional and defensive in nature. It defines a 'fail-closed' posture where the agent is instructed to stop and ask for confirmation before performing any action that could potentially harm the user's data or system integrity.
- [INDIRECT_PROMPT_INJECTION]: The skill includes a dedicated section (Section 5) that explicitly categorizes external content, such as repository files and web data, as untrusted. This serves as a proactive security measure to prevent the agent from following malicious instructions embedded in third-party data.
Audit Metadata