The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install a global NPM package @linkedapi/linkedin-cli if not already present. This is a standard procedure for CLI-based tools but introduces a dependency on the package maintainers.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process content from LinkedIn, including person profiles, posts, comments, and messages. This content is generated by third parties and could potentially contain malicious instructions intended to influence the agent's behavior.
Ingestion points: Commands like linkedin person fetch, linkedin post fetch, and linkedin message get in references/detailed-guide.md bring external data into the agent's context.
Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the fetched data.
Capability inventory: The skill has broad capabilities including sending messages (linkedin message send), creating posts (linkedin post create), and executing workflows (linkedin workflow run).
Sanitization: There is no evidence of sanitization or filtering of the external content before it is processed by the agent.
[DYNAMIC_EXECUTION]: The linkedin workflow run command allows the execution of custom automation workflows defined in JSON format from local files or standard input. This allows the agent to perform complex, multi-step actions based on external configuration files.

linkedin-cli