The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @cargo-ai/cli package from the official npm registry. This is a vendor-owned resource necessary for the skill's primary functionality and is considered a safe dependency.
[COMMAND_EXECUTION]: The skill makes extensive use of the cargo-ai CLI to perform segmentation operations. It also includes utility examples using node -e to parse JSON output, which are localized tools for development and data manipulation.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by fetching data records from external sources. 1. Ingestion points: Record data is retrieved via the segment fetch and change fetch commands in SKILL.md. 2. Boundary markers: No specific delimiters or instructions are provided to the agent to treat fetched data as untrusted. 3. Capability inventory: The agent has access to shell command execution through the cargo-ai binary. 4. Sanitization: No sanitization of the content of the records is described in the provided documentation.

cargo-segmentation