The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions to use curl for interacting with the MaintainX REST API. These commands are typical for testing API connectivity and performing CRUD operations as described in the skill's purpose.
[DATA_EXPOSURE_AND_EXFILTRATION]: The skill initiates network requests to api.getmaintainx.com. This is the official and well-known domain for the MaintainX service. No unauthorized access to local sensitive files or exfiltration to unknown domains was detected.
[CREDENTIALS_UNSAFE]: The implementation examples correctly use the $MAINTAINX_API_KEY environment variable for authentication. This is a secure method for managing API secrets, avoiding hardcoded credentials within the scripts or instructions.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from the MaintainX API and user inputs for work order creation. While this presents a theoretical surface for indirect prompt injection via malformed API responses or descriptions, the risk remains low due to the standard nature of the integration and the lack of high-privilege autonomous actions based on that data.
Ingestion points: API responses from api.getmaintainx.com and user-provided work order fields.
Boundary markers: None explicitly defined in the provided snippets.
Capability inventory: Uses curl for network requests and Bash for script execution.
Sanitization: Standard API response handling is assumed via MaintainXClient and jq usage.

maintainx-hello-world