ai-short-drama-director-kit
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill acts as an organizational framework for directing styles, referencing local paths for modular use. It does not perform network operations or access sensitive system credentials.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user prompts to selectively load creative styles from local files. Mandatory Evidence Chain: 1. Ingestion points: User requests for drama tasks (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Local file reading and text generation. 4. Sanitization: Absent. The risk is assessed as safe because the agent lacks capabilities for command execution or remote data exfiltration.
Audit Metadata