excalidraw

Warn

Audited by Snyk on Feb 17, 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 explicitly fetches and parses arbitrary public URLs in Phase 2 ("Scrape my website" — uses WebFetch on a user-supplied URL) and accepts links/screenshots to "match a reference" and also reads/analyzes user-provided articles/transcripts in Phase 3, so the agent ingests untrusted open-web/user-provided content as part of its workflow, which could enable indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 04:31 AM