setup-agents-md
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from repository files to generate documentation, which could lead to the propagation of malicious instructions if the repository contains compromised configuration files.
- Ingestion points: The agent reads various files including Makefiles, package.json, CI workflows, and environment templates as specified in Step 1 of SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or ignore-markers when the agent is ingesting these external files.
- Capability inventory: The skill performs file system read operations across the repository and file system write operations to create or update the AGENTS.md file.
- Sanitization: There is no requirement for the agent to sanitize or validate the commands and project structure data extracted from the repository files before including them in the output.
Audit Metadata