The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to execute the @useclawlink/cli package. This is the official command-line tool provided by the vendor for managing PhantomBuster integrations.
[COMMAND_EXECUTION]: Interacts with PhantomBuster by executing shell commands. The instructions recommend a security best practice by advising the agent to describe actions and verify inputs with the user before performing any write operations.
[PROMPT_INJECTION]: The skill provides the capability to read external data from PhantomBuster, which represents a surface for indirect prompt injection.
Ingestion points: Data is ingested through actions like phantombuster_get_agent_output and phantombuster_get_leads_by_list documented in SKILL.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore embedded commands within the fetched data.
Capability inventory: The skill utilizes shell command execution via the ClawLink CLI to interact with the service.
Sanitization: No specific filtering or sanitization of the external content is described before it is processed by the agent.
[SAFE]: The storage of authentication tokens in ~/.clawlink/credentials.json following the login command is a standard and documented practice for this CLI tool's credential management.

phantombuster