seedance-interview-short
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied responses to generate creative briefs, creating a potential surface for indirect prompt injection. However, this behavior is central to the skill's primary function as an interview tool, and the risk is mitigated by the skill's focus on text generation without dangerous capabilities.
- Ingestion points: User answers provided during the interview process regarding story beats, video actions, and visual assets (SKILL.md).
- Boundary markers: The skill defines a structured output pattern but does not specify delimiters or protective instructions for the user-provided data.
- Capability inventory: No subprocess calls, file-write operations, or network communications are present in the skill's instructions.
- Sanitization: No explicit sanitization or filtering of user input is described.
Audit Metadata