advibly-claymation-ad
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides pre-formatted shell commands for ffmpeg in references/audio-and-gotchas.md to automate audio mixing, sidechain compression, and framerate adjustments.
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection (Category 8) as it processes data from advibly_get_brand and advibly_get_brand_dossier into generation prompts without explicit boundary markers or sanitization.
- Ingestion points: advibly_get_brand and advibly_get_brand_dossier (SKILL.md).
- Boundary markers: Not present.
- Capability inventory: advibly_generate_image, advibly_generate_video tools, and ffmpeg shell execution.
- Sanitization: No validation of external brand data is specified.
- [EXTERNAL_DOWNLOADS]: The skill instructs the use of curl to fetch media assets from tool-generated URLs for local processing.
Audit Metadata