personalizing-video

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill functions as a procedural guide for video personalization, outlining steps for data mapping and assembly using established tools like Remotion and ElevenLabs.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that ingests external data. 1. Ingestion points: Variant JSON definitions (SKILL.md). 2. Boundary markers: JSON schema structure. 3. Capability inventory: External API calls for TTS and programmatic video rendering. 4. Sanitization: Not specified, but the schema limits input types to text, numbers, and enums.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 04:38 PM