clarify
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for architectural review and does not contain executable code, remote downloads, or malicious logic. All referenced tools appear to be standard platform-level utilities for managing project context and planning.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it processes user-provided architectural proposals. 1. Ingestion points: Phase 1 (Surface & Gap Ingestion) utilizes the /ssot tool to read proposal data. 2. Boundary markers: Structural templates are used for output, but no explicit input delimiters or safety warnings are defined. 3. Capability inventory: The skill can trigger file creation via /changeset and proof-of-concept generation via /spike. 4. Sanitization: No explicit sanitization or input validation logic is defined in the execution protocol.
Audit Metadata