agents-best-practices
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely informational, serving as an architectural guide and checklist for agent development. It does not contain any executable scripts, binaries, or active tool definitions.
- [DATA_EXFILTRATION]: No network operations or sensitive file access patterns were detected. The skill focuses on design principles rather than data processing.
- [REMOTE_CODE_EXECUTION]: There are no external dependencies, package installations, or remote script downloads present in the skill files.
- [PROMPT_INJECTION]: No malicious instructions or bypass attempts were found. The skill specifically provides guidance on mitigating prompt injection and establishing trust boundaries in agentic systems.
Audit Metadata