skills/t0ugh/videoclaw/video-i2i/Gen Agent Trust Hub

video-i2i

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions suggest running uvx videoclaw, which downloads and executes the videoclaw package from a remote registry (PyPI) at runtime. This package is not from a pre-defined trusted organization.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided images which could potentially contain adversarial patterns designed to influence the behavior of the AI model.
  • Ingestion points: Path to input images provided via the -i or --input parameter in the videoclaw i2i command (SKILL.md).
  • Boundary markers: None identified; instructions do not specify delimiters for distinguishing data from commands during image processing.
  • Capability inventory: The skill executes shell commands using videoclaw to transform images and save them to the local filesystem (-o parameter).
  • Sanitization: No evidence of input validation or sanitization for the image files or prompt strings before they are passed to the CLI tool.
  • [COMMAND_EXECUTION]: The skill facilitates the execution of local shell commands through the videoclaw CLI tool to perform image processing tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 10:12 AM