The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on shell scripts (setup.sh and check-result.sh) to execute the muapi command-line utility. These scripts facilitate authentication and data retrieval from the platform.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from an external platform, which creates a potential surface for indirect prompt injection if the API responses contain instructions meant for the agent.
Ingestion points: Data is ingested via muapi predict result and muapi predict wait within check-result.sh.
Boundary markers: None identified; external content is passed directly to the agent's context.
Capability inventory: The skill's primary capability is the execution of the muapi CLI tool for configuration and result polling.
Sanitization: There is no explicit sanitization of the data retrieved from the MuAPI platform before it is displayed.

muapi-platform