agents-md-manager
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from local development project files (such as READMEs and package.json) to automate the generation and auditing of documentation. This creates an ingestion surface where instructions embedded in project files could potentially influence agent behavior.
- Ingestion points: Local project files including
README.md,package.json, source directory structures, and various configuration files (e.g., ESLint, Prettier, Dockerfiles, and CI workflows). - Boundary markers: The skill instructions do not define specific delimiters or instructions to ignore embedded prompts within the ingested project data.
- Capability inventory: The skill has the ability to read and edit local files via the
readandedittools, and perform project stack detection usingproject_init. - Sanitization: There is no explicit requirement for the agent to sanitize or filter the content read from local files before using it to update documentation.
Audit Metadata