anycap-seedance-2
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill provides numerous templates for interacting with the
anycapCLI tool, including commands for video generation (anycap video generate), status checks (anycap status), and automated video review (anycap actions video-read). These operations are consistent with the skill's stated purpose of managing a video generation workflow. - [PROMPT_INJECTION]: The skill implements a prompt compiler pattern that interpolates user-provided scene descriptions and reference details into command-line arguments. While this creates a surface for indirect prompt injection (Category 8), the skill explicitly instructs the agent to verify safety guidelines and intellectual property authorizations (e.g., checking for protected likeness or unauthorized brands) before proceeding with generation, which mitigates the risk of accidental safety bypass.
Audit Metadata