muapi-ai-fight-scene
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to use the muapi command-line interface and standard curl commands to interact with the vendor's API at api.muapi.ai. These interactions are used for authentication, initiating generation tasks, and retrieving the results.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied text to construct prompts for image and video generation models.
- Ingestion points: The character_description, environment_description, action_script, and style_direction parameters defined in SKILL.md are interpolated into prompts.
- Boundary markers: The skill does not employ explicit delimiters or system instructions to prevent the model from potentially following directives embedded within these user-provided strings.
- Capability inventory: The skill is designed to execute local CLI commands (muapi) and perform network operations to a specific vendor API.
- Sanitization: The skill does not mention or implement sanitization or validation of the input text before prompt interpolation.
Audit Metadata