brand-promo-video-generator
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided brand assets and truth sheets, presenting a surface for indirect prompt injection.\n
- Ingestion points: Processes user-provided 'brand truth sheet' and identity-bearing assets in SKILL.md.\n
- Boundary markers: No delimiters or instructions to ignore embedded commands are present.\n
- Capability inventory: Incorporates a multi-staged workflow including 'minimax-h3', 'prompt-qc', and a Python script 'scripts/minimax_h3_prompt_validator.py'.\n
- Sanitization: Lacks input sanitization or filtering for external brand documentation.
Audit Metadata