dojo-model
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Prompt Injection] (SAFE): No malicious instructions or bypass attempts identified.\n- [Data Exposure & Exfiltration] (SAFE): No sensitive data access or exfiltration patterns detected.\n- [Remote Code Execution] (SAFE): No downloads or execution of external code or packages.\n- [Indirect Prompt Injection] (LOW): The skill processes user-provided game concepts to generate structured code. Evidence Chain: (1) Ingestion points: User descriptions in Interactive/Direct mode (SKILL.md); (2) Boundary markers: Absent; (3) Capability inventory: Write, Edit, Read (file tools); (4) Sanitization: Absent in skill definition.
Audit Metadata