README Writer
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for the agent to analyze local project files and generate documentation. It does not contain any suspicious commands, network requests, or obfuscated content.- [DATA_EXPOSURE]: The skill accesses project manifest files such as
package.json,pyproject.toml, andCargo.toml. This access is necessary for extracting project metadata (name, version, dependencies) to create accurate documentation and does not involve accessing sensitive system files or secrets.- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it processes untrusted data from the project's codebase. \n - Ingestion points: Reads project manifest files, source code, and existing documentation. \n
- Boundary markers: None specified in the prompt instructions. \n
- Capability inventory: Limited to file reading and text generation; no subprocess execution or network operations are involved. \n
- Sanitization: None specified. \n Given the limited capabilities (text output only), the risk associated with processing this data is minimal and considered safe.
Audit Metadata