facebook

Warn

Audited by Snyk on Mar 1, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill directly queries user-generated Facebook content via the Graph API (see the "List page posts" curl example that fetches message and comments), so the agent will ingest untrusted third-party posts/comments that could contain instructions influencing behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 05:15 AM