linkedin-skill

Warn

Audited by Snyk on Feb 27, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill directly fetches and parses user-generated LinkedIn content via the LinkedIn API (see SKILL.md commands like "list-posts", "comments" and code calling /rest/posts and /rest/socialActions endpoints), so untrusted third-party posts/comments could be read by the agent and influence subsequent actions (e.g., deciding to comment/react).
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 03:20 PM