shortdrama-asset-pack
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs text-to-text generation based on user-provided scripts. It does not request or use sensitive permissions, network access, or external command execution.
- [SAFE]: Workflow follows best practices by requiring a manual confirmation checkpoint for visual styles and models before generating detailed content, ensuring user oversight.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted script data as its primary input. While this represents a standard attack surface, the risk is mitigated by the skill's lack of executable capabilities and its focus on creative output.
- Ingestion points: Script text and production outlines defined in SKILL.md.
- Boundary markers: Not explicitly defined for input scripts, though output is highly structured.
- Capability inventory: No file system writes, network operations, or subprocess executions are present.
- Sanitization: The skill focuses on transformation into natural language prompts, reducing the risk of functional injection.
Audit Metadata