compose

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell scripts and standard binary utilities such as ffmpeg, ffprobe, and agg to process video assets. These operations are within the scope of its stated functionality.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx to run the Remotion video engine, which potentially involves downloading packages from the public NPM registry.
  • [PROMPT_INJECTION]: The skill processes 'Creative (natural language)' guidance from previous capture stages, creating an indirect prompt injection surface.
  • Ingestion points: Creative guidance handoff (SKILL.md).
  • Boundary markers: None; the guidance is processed as free-text without explicit isolation or instructions to ignore embedded commands.
  • Capability inventory: Execution of render-showcase.sh and npx remotion based on processed props.
  • Sanitization: None; the agent relies on its own interpretation of the natural language to safely construct the showcase JSON props.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 08:32 AM