layer-video-fixes
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve processing external video files and user-defined prompts, which constitutes a potential attack surface for indirect instructions. \n
- Ingestion points: Video files assigned to
init_videoorreference_videoslots, and natural language prompts provided toexecute_forge. \n - Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between the input data and processing instructions. \n
- Capability inventory: The skill utilizes
execute_forge,list_base_models, andget_base_modelfor video generation and modification. \n - Sanitization: No sanitization or filtering of external input is specified. \n- [SAFE]: The skill is authored by 'layerai' and references official vendor resources (
layerai/skills). The instructions follow best practices for the platform, such as estimating prices before execution and using master files to avoid quality loss.
Audit Metadata