content-writer

Warn

Audited by Snyk on Apr 3, 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 explicitly fetches and analyzes arbitrary user-supplied public URLs (e.g., "Step 1: URL Scanning" in Profile Creation: "Fetch each URL using read_url_content") and later re-fetches profile URLs for voice calibration (Phase 3: Execute), meaning untrusted third-party/user-generated content is ingested and directly influences generation decisions and tool actions—exposing the agent to potential indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 3, 2026, 06:05 AM
Issues
1