linkedin

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill prompt instructs the agent to ask the user for tokens and pass them via command-line arguments (linkedin setup --linked-api-token=TOKEN --identification-token=TOKEN), which causes the LLM to handle and expose secret values directly in its output and context.

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

• Third-party content exposure detected (low risk: 0.10). The LinkedIn skill allows fetching profiles, posts, comments, and messages via a CLI tool, which ingests outsider-authored content from public social media profiles and feeds upon user request.