skills/kursku/skills/game-content/Gen Agent Trust Hub

game-content

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns or dangerous operations were found. The skill is designed for developer productivity in a local context.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user narrative requests and references local project files to generate structured JSON data. 1. Ingestion points: User prompts and local game data files (e.g., events.json). 2. Boundary markers: Absent. 3. Capability inventory: Text generation (JSON). 4. Sanitization: None explicitly specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 06:56 AM
Security Audit — agent-trust-hub — game-content