seedance

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides links to the inference-sh GitHub repository for CLI setup and related skills.\n- [COMMAND_EXECUTION]: The skill uses the belt CLI to execute remote video generation tasks.\n- [INDIRECT_PROMPT_INJECTION]: The skill handles user prompts and media URLs as input for video generation.\n
  • Ingestion points: prompt and media URL parameters in SKILL.md.\n
  • Boundary markers: None identified in the instruction examples.\n
  • Capability inventory: belt app run calls for remote processing in SKILL.md.\n
  • Sanitization: Not described in the skill markdown.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 12:00 PM
Security Audit — agent-trust-hub — seedance