video-creative-director

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data which creates an indirect prompt injection surface.\n
  • Ingestion points: External inputs include Brand brief, Campaign brief, Audience, Offer, Brand voice, Visual identity, Platform target, and Product proof or assets (SKILL.md).\n
  • Boundary markers: The instructions do not define delimiters or structural boundaries to isolate user data from system instructions.\n
  • Capability inventory: The skill utilizes video-pattern-reverse-engineer, capabilities/video-understanding, and capabilities/media-generation tools (SKILL.md).\n
  • Sanitization: No technical sanitization or input validation is specified, though the skill provides high-level ethical instructions to avoid deceptive content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 11:49 AM
Security Audit — agent-trust-hub — video-creative-director