seedance-video

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill suggests installing the mcp-seedance package via pip. This is a tool provided by the vendor for integrating with their services.
  • [COMMAND_EXECUTION]: The documentation includes curl command examples to demonstrate how to interact with the API endpoints at api.acedata.cloud.
  • [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to process external data which could potentially contain hidden instructions. 1. Ingestion points: The skill instructions describe an API content array that accepts image_url, audio_url, and video_url from external sources. 2. Boundary markers: The skill does not define specific delimiters or instructions to the model to ignore content within the referenced media. 3. Capability inventory: The skill performs network operations via curl to the vendor's API. 4. Sanitization: There are no explicit sanitization or filtering steps described for the content retrieved from external URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 03:01 PM
Security Audit — agent-trust-hub — seedance-video