The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from the Cargo platform, creating an attack surface where malicious data could potentially influence agent behavior.
Ingestion points: The skill ingest data via cargo-ai orchestration query execute and downloadable CSV/JSON files from run download-outputs as described in SKILL.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between platform data and system instructions.
Capability inventory: The skill utilizes shell command execution across various scripts to interact with the Cargo platform API.
Sanitization: No sanitization or validation mechanisms for the ingested data are mentioned in the documentation or instructions.
[COMMAND_EXECUTION]: The skill's operational logic is built around executing the @cargo-ai/cli tool to perform workspace management and data retrieval. This is consistent with its stated purpose as a vendor-provided analytics tool.

cargo-analytics