logos-and-vectors
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides comprehensive instructions for using vectorization models to create or convert images, which is a standard and benign use case for AI agent skills.- [EXTERNAL_DOWNLOADS]: References to external models such as
recraft:v4-pro@vectorandpicsart:1@1are within the intended operational scope of the vendor (Runware) and do not represent unauthorized or risky downloads.- [PROMPT_INJECTION]: The skill does not contain any instructions that attempt to override the AI agent's safety guidelines, bypass system constraints, or extract internal system prompts.- [DATA_EXFILTRATION]: There is no evidence of the skill attempting to access sensitive local files (e.g., SSH keys, credentials) or transmit unauthorized data to external domains.
Audit Metadata