scene-video-generator

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external input as part of the video generation workflow.
  • Ingestion points: The prompt and reference_image parameters in SKILL.md accept untrusted data from the user or other skills.
  • Boundary markers: The skill does not define explicit delimiters or use instructions to ignore embedded commands within the ingested text.
  • Capability inventory: The skill executes network operations by calling external APIs of AI video backends.
  • Sanitization: No input escaping, validation, or sanitization logic is present to handle potentially malicious prompt content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 06:06 AM
Security Audit — agent-trust-hub — scene-video-generator