muapi-couple-grid-creator
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied images, which introduces a potential vector for indirect prompt injection.\n
- Ingestion points: The
couple_imageinput inSKILL.md.\n - Boundary markers: Absent. The skill does not instruct the model to ignore instructions embedded in the image content.\n
- Capability inventory: The skill uses the
muapiCLI andcurlfor service interaction.\n - Sanitization: None. There is no validation of the image source or content before processing.\n- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands, including
muapiCLI calls andcurlrequests toapi.muapi.ai. These commands are used for authentication and interacting with the primary image generation service.
Audit Metadata