review-architecture
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists solely of markdown and YAML documentation providing instructions for architectural analysis. It does not contain any executable scripts, binaries, or active code components.\n- [PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided code (ingestion point: 'input_schema' in SKILL.md). While this constitutes a surface for indirect prompt injection, the skill lacks any operational capabilities (capability inventory: none detected), such as network access or file system permissions, which precludes the risk of exploitation. No boundary markers or sanitization mechanisms are implemented, which is appropriate for a cognitive-only instruction set.
Audit Metadata