linkedin

Warn

Audited by Snyk on Apr 29, 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 SKILL.md explicitly uses Membrane to connect to LinkedIn and lists actions like list-posts, get-post, list-comments and list-reactions that fetch user-generated LinkedIn content (public third-party data) which the agent would read and could drive follow-up actions such as create-comment or delete-post.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 29, 2026, 02:18 PM
Issues
1