documentation
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data (project source code, API schemas) to generate documentation, which creates a surface for indirect prompt injection.
- Ingestion points: Processes project files, source code, and YAML/JSON API specifications.
- Boundary markers: Absent. There are no instructions or delimiters provided to ensure the agent ignores malicious instructions embedded in the code it is documenting.
- Capability inventory: The skill produces file content (Markdown, YAML, TypeScript comments) that is intended to be written to the local project structure.
- Sanitization: No sanitization or validation logic is specified for the content extracted from processed files.
- [SAFE]: No malicious patterns such as credential harvesting, unauthorized network operations, or obfuscation were detected. The skill correctly promotes the use of environment variables for managing API keys in its examples.
Audit Metadata