muapi-music-video
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (
muapi,curl) using templates that interpolate user-provided values (theme,music_style,visual_style) directly into arguments. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text for use in AI generation prompts. Ingestion points:
theme,music_style, andvisual_styleinput parameters. Boundary markers: Absent; the instructions do not provide delimiters or safety warnings for handling external content. Capability inventory: Execution of CLI tools and network requests viacurl. Sanitization: Absent; no steps are defined to escape or validate user inputs before they are included in commands. - [DATA_EXFILTRATION]: The skill performs network operations to the external service
api.muapi.aito transmit processing requests and retrieve generated assets as part of its primary functionality.
Audit Metadata