feature-deep-dive
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured guidance for code analysis and documentation. It does not contain any executable scripts, network requests, or commands that modify system configuration.
- [DATA_EXPOSURE_EXFILTRATION]: The instructions explicitly include a security-positive constraint: 'Never include secrets or env values. Provider/env var names are fine.'
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data (source code and documentation from a repository) which creates a surface for indirect prompt injection. However, since the skill's capabilities are limited to reading files and writing documentation, the risk of escalation is minimal.
- Ingestion points: Reads files from the local repository (code, schema, documentation).
- Boundary markers: None.
- Capability inventory: Writes documentation files (markdown). No shell execution or network access requested.
- Sanitization: None.
Audit Metadata