skills/zura1555/agents/style-guardian/Gen Agent Trust Hub

style-guardian

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • SAFE (SAFE): No malicious behavior detected. The skill is limited to content formatting and local file management.
  • Indirect Prompt Injection (SAFE): The skill processes external blog text and JSON files, which is an inherent vulnerability surface for data processing tools. 1. Ingestion points: Reads blog drafts and image-manifest.json. 2. Boundary markers: Not present. 3. Capability inventory: Workspace file reading and writing. 4. Sanitization: None identified. The restricted scope of the skill (workspace only) makes this surface acceptable.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:41 PM