add-effect

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run various shell commands for project maintenance and asset generation. Evidence includes bun test src/test, bunx turbo make --filter="@remotion/effects", bunx remotion still, and bun render-cards.ts.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines components that process external data, creating an injection surface. 1. Ingestion points: New effects in packages/effects/src/ process params and source image data. 2. Boundary markers: No explicit data boundary markers are defined for the image processing stream. 3. Capability inventory: The skill can write files to the local disk and execute shader code on the GPU. 4. Sanitization: The skill enforces parameter validation using assertEffectParamsObject and domain-specific validators like validateUnitInterval.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 06:52 PM