linkedin-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs the user/agent to copy Linked API Token and Identification Token and run a CLI command embedding them as command-line arguments (linkedin setup --linked-api-token=TOKEN --identification-token=TOKEN), which requires the LLM to include secret values verbatim in generated output.

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

• Third-party content exposure detected (high risk: 1.00). This skill fetches and ingests user-generated LinkedIn content (profiles, posts, comments, reactions) via the linkedin CLI (e.g., "linkedin person fetch" and "linkedin post fetch") and the agent is expected to read and act on that content (send messages, comment, or run workflows), so untrusted third-party text can influence subsequent actions.