The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes npx to download and execute the @useclawlink/cli package from the NPM registry. This is a vendor-owned package designed to provide the core functionality of the skill.
[COMMAND_EXECUTION]: The skill relies on shell commands to interact with the Instantly API via the CLI tool. This includes commands for authentication (login, connect), discovery (actions, describe), and execution (run).
[CREDENTIALS_UNSAFE]: The documentation identifies that authentication credentials for the service are stored in a local file at ~/.clawlink/credentials.json. While this is a standard practice for the tool's operation, it involves a sensitive file path in the user's home directory.
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it retrieves and processes untrusted data from the Instantly platform, such as email content and lead data.
Ingestion points: Data is ingested through actions like instantly_list_emails, instantly_list_leads, and instantly_list_campaigns which read from the Instantly API.
Boundary markers: There are no explicit instructions or delimiters defined to isolate retrieved external content from the agent's internal instructions.
Capability inventory: The agent possesses the capability to execute shell commands and perform network operations through the integrated CLI tool.
Sanitization: The instructions do not specify any sanitization, filtering, or validation of the data retrieved from external sources before it is processed by the agent.

instantly