asset-style-check

Pass

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as asset lists and visual briefs to generate style consistency reports. 1. Ingestion points: candidate_asset_list and brief_style_direction in contract.json and SKILL.md. 2. Boundary markers: None explicitly defined to isolate untrusted input. 3. Capability inventory: The skill explicitly forbids execution of Blender, Python, or shell commands, operating solely as a logic-based validator. 4. Sanitization: No data sanitization logic is present.
  • [NO_CODE]: The skill is entirely declarative and does not include any scripts, binary files, or package dependencies.
  • [SAFE]: No malicious patterns, obfuscation, or persistence mechanisms were detected. The skill is well-scoped and adheres to safety-by-design by strictly limiting its capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 7, 2026, 09:09 PM