muapi-ad-creative
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill performs network operations by sending requests to
api.muapi.aifor image generation and task polling. - [COMMAND_EXECUTION]: The skill executes local
muapiCLI tools (e.g.,muapi image generate,muapi auth configure) and usescurlfor direct interaction with the MuAPI API endpoints. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input via
product_or_serviceandtarget_audiencefields. These values are interpolated into prompts for image generation and ad copy creation. While this presents a surface for prompt injection, the risk is restricted to the generated creative content and does not facilitate system-level compromise.
Audit Metadata