agents-md
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted repository data which presents an indirect prompt injection surface. It is instructed to read various documentation files (README.md, CONTRIBUTING.md, existing agent instructions) to audit or migrate content. Since these files are part of the target repository and could be modified by an attacker, they may contain malicious instructions designed to influence the agent's behavior during the drafting or validation phase.
- Ingestion points: The skill reads AGENTS.md, README.md, CONTRIBUTING.md, CI workflows, and package scripts in the target repository.
- Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when reading these external files.
- Capability inventory: The skill has the capability to write and modify files (AGENTS.md) on the file system.
- Sanitization: The skill does not mention specific sanitization or validation of the text content extracted from the repository files before it is processed into the new AGENTS.md file.
Audit Metadata