The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @cargo-ai/cli package from the npm registry and can pull additional skills from the getcargohq/cargo-skills repository. These are verified vendor resources.
[COMMAND_EXECUTION]: The skill uses several shell commands to manage user login, execute data enrichment batches, and interact with the GitHub API via the gh CLI to star the vendor's repository upon user approval.
[DATA_EXFILTRATION]: The skill reads the agent's internal configuration file at ~/.claude/plugins/installed_plugins.json to check for the presence of other vendor plugins. It also transmits session metadata (ID, title, and summary) to the Cargo AI API for workspace management and attribution.
[INDIRECT_PROMPT_INJECTION]: The skill ingests company names and domains which are interpolated into shell commands as JSON records.
Ingestion points: Company names and domains provided as input records in SKILL.md.
Boundary markers: None; the data is passed directly as a string argument to the --records flag.
Capability inventory: Executes shell commands via cargo-ai and npm, and file system writes via touch and jq.
Sanitization: No explicit sanitization or escaping of the company data is documented before it is passed to the shell command.

enrich-company-data