creative-ads-explorer
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows best practices for a creative assistant tool, focusing on generating prompts and organizing data within a matrix.
- [DATA_EXFILTRATION]: No network operations or access to sensitive local files (such as credentials or SSH keys) are present. Activity is confined to the local workspace directory
./creative/ads/. - [PROMPT_INJECTION]: The instructions do not attempt to override agent safety guidelines, extract system prompts, or utilize jailbreak-style language.
- [REMOTE_CODE_EXECUTION]: The skill does not download external scripts or packages. It references an image-generation tool, which is a standard capability for AI agents in this context.
Audit Metadata