agents-md-writer
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that involves reading repository content (scripts, documentation, and configuration files) to inform the creation of agent instructions. This creates an attack surface where untrusted repository data could attempt to influence the agent's output. This is a common characteristic of auditing tools and is documented here as a potential risk factor.
- [EXTERNAL_DOWNLOADS]: The skill includes a link to the official OpenAI documentation for the AGENTS.md standard. This reference targets a well-known and trusted service.
Audit Metadata