linkedin-message-agent
Warn
Audited by Snyk on Apr 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The agent automates a browser to open LinkedIn messaging and directly reads user-generated conversation text from the page (see SKILL.md workflow step "Navigate to LinkedIn Messaging inbox" and scripts/linkedin-message-agent.js where evaluate(...) scrapes the last messages and generateResponse(...) uses that content to decide and send replies), so untrusted third-party messages can influence its actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata