find-features

Pass

Audited by Gen Agent Trust Hub on May 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs codebase analysis to discover undocumented features and generates documentation files using local templates. All operations are local to the repository and use standard agent interactions.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted codebase content to generate documentation. * Ingestion points: Reads various project files including AGENTS.md, AGENTS_FEATURES.md, and CONTEXT.md. * Boundary markers: None explicitly defined to isolate code content during documentation generation. * Capability inventory: File system read and write for markdown documentation generation. * Sanitization: Relies on user review of the generated output before committing changes to the repository.
Audit Metadata
Risk Level
SAFE
Analyzed
May 25, 2026, 01:12 PM
Security Audit — agent-trust-hub — find-features