Technical Documentation
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is instructional in nature and provides templates for documentation without including executable code, hidden payloads, or suspicious network operations.
- [PROMPT_INJECTION]: The skill processes untrusted project files to generate documentation, which creates a surface for indirect prompt injection if those files contain malicious instructions. This risk is minimized by the skill's limited toolset, which lacks network exfiltration or remote code execution capabilities.
- Ingestion points: Project code and documentation are read using the Read, Grep, and Glob tools.
- Boundary markers: No explicit delimiters are specified to separate untrusted code content from documentation instructions.
- Capability inventory: The skill is restricted to local filesystem operations including Write, Edit, Read, Grep, and Glob.
- Sanitization: No specific sanitization or escaping of ingested file content is mentioned.
Audit Metadata