experts
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for a legitimate development workflow involving asset generation. It utilizes well-known command-line utilities (
ffmpeg,avconvert) and project-specific tools (bunx remotion,bun render-cards) to process local files. - [INDIRECT_PROMPT_INJECTION]: The skill identifies a data ingestion surface where external data influences agent actions, though the risk is negligible in context.
- Ingestion points: Content is read from
packages/promo-pages/src/components/experts/experts-data.tsxto drive video and card rendering. - Boundary markers: Absent; the instructions assume the source file is a trusted part of the repository.
- Capability inventory: Includes file system operations (
cp), video processing (ffmpeg), and executing project-specific build scripts (bun render-cards). - Sanitization: No specific sanitization or validation of the input data is performed before it is passed to rendering tools. This surface is characteristic of the skill's primary purpose and does not introduce significant risk given the local development scope.
Audit Metadata