muapi-character-story-video
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill takes user-provided strings for character descriptions and story premises and interpolates them directly into prompts for image and video generation tools.
- Ingestion points: External data enters the context via the
character_descriptionandstory_premiseinputs defined in SKILL.md. - Boundary markers: There are no explicit delimiters or specific instructions for the agent to sanitize or ignore instructions potentially embedded within user inputs.
- Capability inventory: The skill possesses the ability to execute image generation, editing, and video animation via the
muapiCLI andcurlrequests. - Sanitization: No input validation or escaping mechanisms are described before interpolation into the task prompts.
- [COMMAND_EXECUTION]: The skill requires the execution of shell-based commands including the
muapiCLI andcurlfor API interaction. This involves passing user-supplied content as arguments to these tools, which is a standard functional requirement for this skill but represents a technical interface for command execution.
Audit Metadata