linkedin

Warn

Audited by Snyk on Mar 13, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly exposes LinkedIn user-generated content via actions like "list-posts", "get-post", and "list-comments" (and via Membrane proxy requests to LinkedIn endpoints), so the agent will fetch and read untrusted third-party posts/comments that could influence subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 13, 2026, 10:44 AM
Issues
1