linkedin-coach

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly requires researching and ingesting public LinkedIn content (e.g., site:linkedin.com web searches, LinkedIn profile URLs, and user posts) and directs the agent to analyse those user-generated social media posts as part of core workflows (see references/content-strategy-coaching.md and references/linkedin-posts-helper.md), which exposes the agent to untrusted third‑party content that can influence its decisions and actions.