digital-avatar

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and process user-provided content (descriptions, scripts, and audio) for video generation, creating a surface for potential indirect instructions.
  • Ingestion points: Parameters such as description, text, audio_sample, and audio in SKILL.md accept untrusted user data.
  • Boundary markers: The skill instructions do not define specific delimiters or instructions to prevent the agent from obeying commands embedded within user-supplied content.
  • Capability inventory: The skill performs network operations by calling external APIs for Kling, Jimeng, HeyGen, D-ID, and Synthesia as described in SKILL.md and references/backend-setup.md.
  • Sanitization: No explicit input validation or sanitization mechanisms are specified in the provided files.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 06:07 AM
Security Audit — agent-trust-hub — digital-avatar