The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to download and execute the @useclawlink/cli package from the NPM registry, which is the primary mechanism for the tool's functionality.
[COMMAND_EXECUTION]: The skill interacts with RocketReach by executing shell commands via the ClawLink CLI to search for people, companies, and professional details.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect injection as it ingests user-provided text for search queries and action descriptions which are then passed into the CLI tool.
Ingestion points: User input strings passed to the npx @useclawlink/cli actions and run commands in SKILL.md.
Boundary markers: None explicitly present in the command examples, though standard shell quoting is used.
Capability inventory: The skill uses subprocess calls to execute CLI commands but does not have arbitrary file-write or general network capabilities outside the specific CLI tool.
Sanitization: Relies on the underlying CLI tool's handling of input strings.
[SAFE]: The resources and packages used originate from the vendor's infrastructure, and the local storage of credentials at ~/.clawlink/credentials.json follows standard practices for CLI-based authentication.

rocketreach