linkedin-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to ask the user for Linked API and Identification tokens and to run a CLI command that embeds those tokens directly as command-line arguments, requiring the LLM to include secret values verbatim in its output.

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

• Third-party content exposure detected (high risk: 0.75). The required workflow includes fetching LinkedIn profiles/posts/comments (e.g., linkedin person fetch <url>, linkedin post fetch <url> --comments), whose returned JSON can contain outsider-authored free text (names, headlines, post/comment bodies) that the agent would ingest into its LLM context.