kaleidoscope
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied images which represents a potential surface for indirect prompt injection.
- Ingestion points: User-provided images as described in Step 2 of SKILL.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded content are provided.
- Capability inventory: Uses ffmpeg for media processing and view_image for inspection.
- Sanitization: No explicit sanitization or image validation steps are defined.
- [COMMAND_EXECUTION]: The instructions include specific shell commands for ffmpeg to extract frames and create contact sheets. While this involves command execution, it is directly related to the skill's primary function of media processing.
Audit Metadata