seedance-2-0
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the construction of complex AI prompts by interpolating user-provided text (e.g., the
PROMPTvariable) into structured cinematic templates. This creates a surface where malicious user input could potentially attempt to influence the behavior of the downstream video generation models.- Ingestion points: User-provided text is ingested via thePROMPTargument in thevideo_selectorandseedance_videotool execution examples.- Boundary markers: The skill does not define explicit boundary markers or instructions to ignore embedded commands within the user-supplied prompt sections.- Capability inventory: The skill utilizes thevideo_selector,seedance_video, andseedance_replicatetools to interact with external video generation APIs.- Sanitization: No sanitization or input validation logic is described in the skill documentation.
Audit Metadata