venice-video
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted inputs such as user-provided prompts and external URLs which are passed to the Venice API.\n
- Ingestion points: Parameters including
prompt,image_url,video_url, and YouTubeurlin SKILL.md.\n - Boundary markers: The instructions do not define specific delimiters for separating user content from system instructions.\n
- Capability inventory: The skill facilitates network requests to the vendor's API endpoint at api.venice.ai.\n
- Sanitization: The instructions do not include explicit steps for sanitizing or validating external content before processing.
Audit Metadata