drama-planner
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Safe (SAFE): The skill was audited across all 10 threat categories and no malicious patterns were detected. There is no evidence of command execution, data exfiltration, or obfuscation. The skill correctly identifies its intended tool usage ('Read') for internal documentation.- Indirect Prompt Injection (SAFE): The skill ingests untrusted user content (story ideas), which constitutes a potential attack surface. However, the risk is negligible because the skill lacks dangerous capabilities such as network access, file writing, or shell execution. Evidence: 1. Ingestion: User-supplied story ideas and outlines via SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: 'Read' tool only, used for local reference files. 4. Sanitization: None explicitly defined.
Audit Metadata