seedance-2-0-short-drama-video

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the 'requests' Python package via pip to facilitate network communication.
  • [COMMAND_EXECUTION]: The skill relies on the execution of a Python script ('videogen.py') to process media and interface with the generation API.
  • [DATA_EXFILTRATION]: User-provided prompts and media files are transmitted to 'ai-hive.iclip.cn' for processing. While this is the intended purpose of the skill, the domain is not on the standard whitelist.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides an interface for sending untrusted user content to a remote API, representing an indirect injection surface.
  • Ingestion points: User prompts and file paths ingested via CLI arguments in 'scripts/videogen.py'.
  • Boundary markers: The skill does not implement delimiters or safety instructions to separate user data from API prompt structures.
  • Capability inventory: The script performs local file reads, writes, and network POST requests.
  • Sanitization: There is no evidence of input validation or sanitization before the data is sent to the remote service.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 12:20 PM
Security Audit — agent-trust-hub — seedance-2-0-short-drama-video