linkedin-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the user/agent to collect the Linked API Token and Identification Token and to embed them directly into a CLI command (linkedin setup --linked-api-token=... --identification-token=...), which requires the LLM to handle and output secret values verbatim.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). The required workflow can fetch LinkedIn profile/post/comment text from user-supplied URLs (e.g., linkedin person fetch <url> / linkedin post fetch <url>), and that outsider-authored free text is returned as readable JSON that the agent would ingest into LLM context.