The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @cargo-ai/cli package from the NPM registry to provide the necessary functionality for LinkedIn URL resolution. This is an official vendor-provided tool required for the skill's operation.
[COMMAND_EXECUTION]: The skill makes extensive use of local command-line tools including npm, cargo-ai, grep, jq, and the gh (GitHub) CLI to perform its tasks and manage the environment.
[DATA_EXFILTRATION]: The skill reads the ~/.claude/plugins/installed_plugins.json file. This access is used to check for the presence of the cargo@gtm plugin to ensure the skill does not conflict with or duplicate the functionality of the full plugin pack. While used for logic, this constitutes access to local environment state.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection. It takes user-provided data, such as person names and company names, and places them into shell command arguments for execution.
Ingestion points: Contact details provided by the user are processed in the Do the job section.
Boundary markers: There are no specific instructions or delimiters used to sanitize or isolate the user-provided data within the shell commands.
Capability inventory: The skill can perform network requests via cargo-ai and gh, and read local files.
Sanitization: No explicit sanitization or validation steps are defined in the instructions; it relies on the agent's ability to format the JSON records correctly.
[REMOTE_CODE_EXECUTION]: The skill uses npx skills add getcargohq/cargo-skills to dynamically add additional functionality. This involves downloading and executing code from an external registry to extend the agent's capabilities.

find-linkedin-url