The Agent Skills Directory

[SAFE]: The skill serves as a reference guide for the Cargo orchestration platform. All documented tools, APIs, and CLI commands (@cargo-ai/cli) are official vendor resources belonging to getcargohq.
[DYNAMIC_EXECUTION]: The skill documents the platform's native support for JavaScript (script) and Python nodes within workflows. This is a primary feature of the orchestration service, and the JavaScript environment is restricted to a predefined allowlist of modules (e.g., axios, lodash, uuid).
[INDIRECT_PROMPT_INJECTION]: The skill describes an attack surface for indirect prompt injection as it processes data from external sources like CSV files and database models.
Ingestion points: Data enters the agent's context through run create, batch create, and segment fetch operations from external files and models.
Boundary markers: The platform uses {{ }} template tags for interpolating data into node configurations.
Capability inventory: The platform possesses capabilities to perform API calls (connectors), HTTP requests, SQL execution, and custom script execution.
Sanitization: Documentation demonstrates the use of expressions for data transformation and normalization, although specific platform-level sanitization for interpolated prompt content is not explicitly detailed in the provided references.

cargo-orchestration