short-drama-scriptwriter
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided story outlines and original materials for adaptation, which establishes an attack surface for indirect prompt injection.
- Ingestion points: User-supplied '故事梗概/原著素材' (story outlines) and '对标爆款' (competitor examples) as defined in the Step 1 workflow.
- Boundary markers: The skill does not provide delimiters or specific instructions for the agent to distinguish between story data and control instructions.
- Capability inventory: The agent uses the 'read_reference' tool to access local configuration and generates text outputs.
- Sanitization: No sanitization or validation of the input story text is specified in the instructions.
Audit Metadata