The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes npx @useclawlink/cli to fetch and run the vendor's command-line interface from the NPM registry.
[COMMAND_EXECUTION]: Instructions direct the agent to execute shell commands for authentication (login), service connection (connect), and running specific Lemlist operations (run, describe, actions).
[DATA_EXFILTRATION]: The skill documentation identifies ~/.clawlink/credentials.json as the local path where authentication credentials are stored by the CLI.
[INDIRECT_PROMPT_INJECTION]: The skill facilitates the retrieval of external data from Lemlist (including campaign details, lead information, messages, and activity logs) which is then processed by the agent.
Ingestion points: Data is ingested through actions such as lemlist_get_contact_messages, lemlist_get_campaign_sequences, and lemlist_get_retrieve_activities.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded content within retrieved data.
Capability inventory: The agent has the capability to execute shell commands and interact with the Lemlist API based on the retrieved data.
Sanitization: No explicit sanitization or validation steps for retrieved external content are provided in the skill instructions.

lemlist