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, and DESIGN.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, and DESIGN.md in 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
Risk Level
SAFE
Analyzed
Jun 19, 2026, 07:12 AM
Security Audit — agent-trust-hub — ai-eval-review