creativeclaw-create-ugc-ad
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements a professional creative workflow that explicitly instructs the agent not to share private data, local file paths, or conversation history with external tools.- [SAFE]: External dependencies and documentation links are limited to established and well-known AI service providers (Google, OpenAI, HeyGen, Kling, Volcengine, Fal.ai) and the vendor's own platform infrastructure.- [INDIRECT_PROMPT_INJECTION]: The skill processes external user-supplied data such as product scripts and media files. It mitigates potential risks by providing instructions to sanitize unverified claims and by operating within the host LLM's safety boundaries.
Audit Metadata