feature-spec

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its ingestion of external project files.
  • Ingestion points: Uses 'vision.md', 'requirements.md', and the 'backend/'/'frontend/' codebases as primary context.
  • Boundary markers: Does not define any delimiters or 'ignore' instructions to separate feature requirements from the agent's own behavioral instructions.
  • Capability inventory: Capable of reading arbitrary files in the repository and writing multiple markdown files including 'spec.md' and 'design-brief.md'.
  • Sanitization: No sanitization or content validation is applied to the ingested documentation before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 05:02 PM