video-generator

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes external resources for background music, specifically instructing the agent to search and download royalty-free tracks from well-known services like Pixabay and YouTube Audio Library. This is a functional requirement for the video creation process.
  • [PROMPT_INJECTION]: The skill processes user-supplied descriptions (narrative arc, character appearance) to generate prompts for image and video tools. While this represents a standard indirect prompt injection surface, the risk is mitigated by a structured workflow that includes mandatory user confirmation steps.
  • Ingestion points: Phase 1 (Initial) gathers requirements including purpose, narrative arc, and character descriptions from the user.
  • Boundary markers: The workflow includes a mandatory stop for user confirmation in Phase 1 before generating global definitions, although it lacks explicit delimiters for user-provided data within tool prompts.
  • Capability inventory: The skill uses image generation, image variation, text-to-speech, and web search/download tools.
  • Sanitization: There is no explicit text sanitization mentioned, but the skill mandates detailed human-readable descriptions rather than passing raw user input directly to executable code.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 02:53 PM
Security Audit — agent-trust-hub — video-generator