cw-structure

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFE
Full Analysis
  • SAFE (SAFE): The skill is a set of instructions for project organization. It does not involve any command execution, network access, or suspicious data handling.
  • Indirect Prompt Injection (SAFE): The skill processes user-provided project descriptions to generate a structural map in ./docs/structure.md. While it lacks explicit boundary markers for untrusted data, the risk is negligible as the skill's capabilities are limited to documentation and do not include code execution or external communication. Ingestion points: user project descriptions and fragments (Step 1); Boundary markers: absent; Capability inventory: Read, Grep, Glob, Write, Edit; Sanitization: absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 10:39 AM