muapi-one-shot-video
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input via the
sceneandstyleparameters and interpolates them directly into a prompt template for the video generation model. - Ingestion points:
sceneandstyleinputs inSKILL.md. - Boundary markers: None present; inputs are placed directly into the prompt string.
- Capability inventory: Executes
muapiCLI commands andcurlnetwork requests to external APIs. - Sanitization: No escaping or validation is performed on the user-provided text before interpolation.
- [COMMAND_EXECUTION]: The skill uses the
muapiCLI andcurlto interact with theapi.muapi.aiservice. This involves accessing theMUAPI_API_KEYenvironment variable and performing network operations to the vendor's API endpoint.
Audit Metadata