linkedin-personal-branding

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs the agent to access and scrape live LinkedIn pages (Step 2: use chrome-devtools MCPs like list_pages/select_page/take_snapshot and navigate_page to linkedin.com/in/[user]/recent-activity/ and linkedin.com/sales/ssi), thereby ingesting untrusted, user-generated third-party content that the agent must read and that can materially alter its analysis and follow-up actions.