writing-agents-md
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily focused on generating and reviewing documentation (AGENTS.md) based on existing repository files. It does not perform network operations or access sensitive system credentials.
- [SAFE]: The instructions explicitly forbid the inclusion of secrets, credentials, private URLs, or any content that encourages bypassing security checks in the generated files.
- [SAFE]: The skill promotes secure and reliable practices by instructing the agent to ground its suggestions in verifiable evidence from configuration files and CI definitions rather than inventing commands.
- [SAFE]: While the skill processes repository data which could contain indirect prompt injections, the lack of dangerous capabilities (like network exfiltration or shell execution) and the focus on documentation output make this a safe utility.
Audit Metadata