short-drama-kit
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill operates within the scope of its intended creative purpose using specific media tools.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied premises for script generation, which is a standard input surface for generative tasks. 1. Ingestion points: User-provided premise, number of characters, and voice preferences within SKILL.md. 2. Boundary markers: Absent; the instructions do not specify delimiters for external input. 3. Capability inventory: Uses voice_clone, tts, generate_music, generate_image, and generate_video tools. 4. Sanitization: Absent; the skill relies on the model's internal safety guardrails for content generation.
Audit Metadata