The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes the @useclawlink/cli package from the official NPM registry, a well-known and trusted service. This package is maintained by the skill's author and is used to facilitate the integration.
[COMMAND_EXECUTION]: Instructs the agent to use npx to execute the ClawLink CLI for logging in, connecting accounts, and performing LinkedIn actions. These operations are standard for the tool's intended purpose.
[PROMPT_INJECTION]: The skill processes untrusted data from LinkedIn, representing an indirect prompt injection attack surface.
Ingestion points: Retrieves external data such as post content, comments, and member profiles from LinkedIn (e.g., via linkedin_get_post_content).
Boundary markers: The instructions do not define specific delimiters for separating external content from system instructions.
Capability inventory: The skill includes write capabilities such as linkedin_create_linked_in_post and linkedin_create_comment_on_post.
Sanitization: There is no explicit documentation of sanitization or filtering of ingested data before it is processed by the agent.

linkedin