feature-vision
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data which could contain malicious instructions.
- Ingestion points: Reads a development guide from
~/.local/share/dotfiles/ai/guides/feature-development-process.mdand user-provided notes files (e.g.,@notes.md). - Boundary markers: No explicit boundary markers or 'ignore' instructions are used when interpolating file content into the prompt.
- Capability inventory: The skill has file-writing capabilities, creating
vision.md,future.md, anddiscussion-summary.mdbased on the processed content. - Sanitization: No sanitization or validation of the external file content is performed before processing.
Audit Metadata