founder-product-video
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a 'Cost transparency gate' requiring explicit user confirmation ('proceed') before initiating paid MCP tool calls, protecting against unintended expenditures.
- [SAFE]: Includes an automated 'Avatar-type probe' using media analysis to classify character references and stop generation if recognizable trademarked or copyrighted characters (e.g., Disney/Marvel characters) are detected.
- [SAFE]: Employs a deterministic deterministic UI overlay and OCR QA process (Step 5.5) to verify that brand names and product text are rendered correctly, preventing the 'hallucinations' or garbled text common in AI video generation.
- [SAFE]: The use of Base64 encoding for fonts in Step 9 is documented as a technical requirement for embedding assets in headless browser renders and does not constitute malicious obfuscation.
- [SAFE]: The skill uses unique seeds for generation tasks to avoid replaying cached failures, demonstrating robust error-handling practices.
Audit Metadata