skills/skillsrouter/skills/video-edit/Gen Agent Trust Hub

video-edit

Pass

Audited by Gen Agent Trust Hub on May 22, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the 'sr' CLI tool (associated with the vendor skillsrouter) through Bash to execute video transformation tasks. This is standard functionality for the skill's stated purpose.
  • [PROMPT_INJECTION]: The skill processes user-supplied natural language prompts to guide video editing, which constitutes an indirect prompt injection surface.
  • Ingestion points: User input provided in the 'prompt' field of the JSON payload in SKILL.md.
  • Boundary markers: None; input is passed directly to the model configuration.
  • Capability inventory: The skill is restricted to executing the 'sr' tool via Bash as specified in the frontmatter.
  • Sanitization: No explicit sanitization or filtering of the user prompt is defined within the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 22, 2026, 08:59 AM