perfect-design

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill incorporates an indirect prompt injection surface by consuming data from a local file to determine tool routing and workflow steps.
  • Ingestion points: The skill reads the contents of 'ux.md' (Step 2) and accepts user-provided URLs (Step 1) for analysis.
  • Boundary markers: The instructions do not specify the use of delimiters or instructions to ignore embedded commands within the ingested content.
  • Capability inventory: The skill coordinates agent actions by triggering slash commands for specialized tools (e.g., '/audience-research', '/persona-archetypes') and performing file-write operations to update the project state.
  • Sanitization: There are no explicit validation or sanitization routines mentioned for the content read from external files or URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 12:35 AM
Security Audit — agent-trust-hub — perfect-design