ai-eval-review
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external files (such as
ai-ux-review.md,validation-canvas.md, andDESIGN.md) within the user's project to generate its audit results. - Ingestion points: The skill reads project-internal files including
ai-ux-review.md,validation-canvas.md, andDESIGN.mdin Phase 0 (Intake) and during block-specific elicitation. - Boundary markers: The instructions lack specific boundary markers or 'ignore embedded instructions' warnings for the data being read from these files.
- Capability inventory: The skill has file system read/write access to the local project directory but does not possess network or arbitrary subprocess capabilities.
- Sanitization: No sanitization or validation of the input file content is defined in the skill's logic.
Audit Metadata