The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @cargo-ai/cli package from npm. This is the official command-line interface provided by the vendor (getcargohq) and is necessary for the skill to function.
[COMMAND_EXECUTION]: The skill utilizes the cargo-ai CLI to perform operations such as listing, uploading, and removing files. These commands are executed to manage workspace knowledge and are not used for malicious purposes.
[DATA_EXFILTRATION]: The skill includes functionality to upload files (PDFs, CSVs, text) to the Cargo platform via cargo-ai content file upload. This is a core feature intended for building knowledge libraries and does not appear to target sensitive system files or credentials.
[INDIRECT_PROMPT_INJECTION]: The skill manages external data (files) that are used to ground agent responses. While this presents a potential surface for indirect prompt injection from malicious content within those files, it is a standard part of RAG functionality.
Ingestion points: cargo-ai content file upload --file-path <path>
Boundary markers: None specified in the instructions.
Capability inventory: None; the skill manages the storage of data rather than providing execution capabilities in this context.
Sanitization: None specified; the skill assumes the user is uploading trusted knowledge base content.

cargo-content