w-architecture

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No security issues were detected. The skill performs standard text processing and file management tasks consistent with its stated purpose of architecture planning.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes local architecture documentation (MDX and ADR files) as input to generate implementation plans. Ingestion points: Architecture MDX and ADR files in SKILL.md. Boundary markers: None present. Capability inventory: Reading local files and writing generated plans to chat or specific paths. Sanitization: No explicit content validation. The surface is considered safe due to the lack of high-risk capabilities like network or code execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 12:07 AM
Security Audit — agent-trust-hub — w-architecture