assets-oriented-generate

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): No instructions attempting to bypass safety filters or override agent behavior were found.
  • [Indirect Prompt Injection] (SAFE): The skill processes user-provided prompt rows to generate assets. 1. Ingestion points: User-defined prompt rows in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Execution of a local python script (scripts/generate_assets.py). 4. Sanitization: Not specified.
  • [Command Execution] (SAFE): The skill executes a local script for its primary purpose with no suspicious parameters or elevated privileges.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:35 PM