linkedin-profile-optimizer

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

• Third-party content exposure detected (high risk: 0.90). The skill's required intake (Step 1: "To get started, paste the following" — including the full About section and experience entries from LinkedIn) instructs the user to supply raw LinkedIn/profile content that the agent must read and use to score and rewrite the profile, so untrusted, user-generated third-party text from social media is clearly ingested and can materially influence the agent's outputs and actions.