muapi-keyboard-art-maker
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
muapiCLI andcurlto process image generation requests through the vendor's API endpoints.\n- [INDIRECT_PROMPT_INJECTION]: User-supplied text is interpolated into the image generation prompt, which provides a surface for indirect prompt injection.\n - Ingestion points: The
display_textinput variable inSKILL.mdis directly embedded into the prompt template.\n - Boundary markers: No delimiters or boundary markers are used to isolate the user-provided text within the prompt.\n
- Capability inventory: The skill has the capability to execute
muapiCLI commands and perform network requests viacurl.\n - Sanitization: No sanitization, escaping, or validation is applied to the
display_textinput before it is passed to the generation model.
Audit Metadata