seedance-ad-creative

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local shell script (ofox-video.sh) to perform video generation tasks, including job submission and status polling.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to construct prompts for the video API, creating an injection surface.
  • Ingestion points: User-provided text descriptions and file paths for product photos (SKILL.md).
  • Boundary markers: Absent; user input is interpolated directly into command arguments.
  • Capability inventory: Shell command execution and network operations (via curl).
  • Sanitization: No explicit sanitization or validation of user-provided strings is documented.
  • [EXTERNAL_DOWNLOADS]: The skill downloads generated video assets from the vendor's official domain (app.ofox.ai).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 07:02 AM
Security Audit — agent-trust-hub — seedance-ad-creative