architect

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data by reading the codebase to understand architecture (File: SKILL.md, Step 1). Mandatory Evidence: 1. Ingestion point: Read codebase step. 2. Boundary markers: Absent. 3. Capability inventory: File-write to 'docs/tasks/'. 4. Sanitization: Absent. This creates a surface for indirect prompt injection where malicious instructions hidden in code comments could influence the generated PRD content.
  • [NO_CODE]: The skill consists solely of Markdown definition and template files. No executable code or scripts are provided within the skill package.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 05:27 PM