agents-md-generator
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze the repository content to extract patterns and conventions, which creates a potential surface for processing untrusted instructions embedded in the codebase.
- Ingestion points: Phase 1 (Repository Analysis) requires the agent to analyze the codebase for tech stacks, directory structures, and key patterns in the local files.
- Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious embedded content within the analyzed files.
- Capability inventory: The skill asks the agent to generate and present multiple Markdown files (AGENTS.md). While it does not invoke network or shell tools directly, the generated content is influenced by the analyzed input.
- Sanitization: There are no specified methods for sanitizing or validating the patterns and code snippets extracted from the repository before they are included in the final documentation.
Audit Metadata