The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to download and execute the @useclawlink/cli package from the NPM registry. This tool belongs to the skill's authoring organization and is used to facilitate the connection between the AI agent and the LinkedIn API.
[COMMAND_EXECUTION]: The skill directs the agent to execute shell commands via the @useclawlink/cli tool. These commands are used to manage authentication, list available actions, and execute specific LinkedIn operations such as posting or reading profile data.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill ingests untrusted external data from LinkedIn, including post content, member profiles, and comments, through actions like linkedin_get_post_content and linkedin_list_reactions in SKILL.md.
Boundary markers: The skill includes a manual instruction stating "confirm with the user before any write" to prevent unauthorized actions.
Capability inventory: The skill has the capability to execute write operations (e.g., linkedin_create_linked_in_post, linkedin_create_comment_on_post) and read operations using shell commands via the CLI.
Sanitization: There is no explicit mention of data sanitization or filtering of the content retrieved from LinkedIn before it is processed by the agent.

linkedin