MeiGen Visual Creative Expert
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious instructions, prompt injections, or obfuscated code patterns were found in the skill definition.
- [COMMAND_EXECUTION]: The skill uses the
Tasktool to delegate image generation to a specializedmeigen:image-generatorsubagent. This is a secure architectural pattern for isolating sensitive tool calls. - [EXTERNAL_DOWNLOADS]: The skill references image URLs and gallery resources from the
meigen.artdomain, which is consistent with the skill's primary purpose and vendor identity. - [DATA_EXFILTRATION]: The skill includes explicit safety rules, such as Rule 3, which forbids the agent from reading saved image files from the local filesystem, effectively preventing unauthorized data access or exposure.
Audit Metadata