muapi-ugc-ads-workflow
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: Employs the
muapiCLI andcurlto interface with MuAPI endpoints (api.muapi.ai) for media processing.\n- [EXTERNAL_DOWNLOADS]: Connects to api.muapi.ai to send image data and receive generated content.\n- [DATA_EXFILTRATION]: Correctly utilizes the MUAPI_API_KEY environment variable for authentication, following standard security practices for secret management. No unauthorized data harvesting was detected.\n- [PROMPT_INJECTION]: Ingests theproduct_namevariable into prompts and search queries for the primary purpose of content generation.\n - Ingestion points:
product_nameinput in SKILL.md.\n - Boundary markers: None present for input interpolation.\n
- Capability inventory: Web search,
muapiCLI, andcurlfor API interaction.\n - Sanitization: No explicit sanitization or validation of the input text is performed.
Audit Metadata