blog-brief

Warn

Audited by Snyk on Mar 7, 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). Yes — the SKILL.md workflow explicitly instructs the agent to use "WebSearch" in Step 2, analyze the "top 3-5 ranking pages" in Step 3, and perform statistics research recording source URLs in Step 4, which requires fetching and interpreting untrusted public web content that can influence briefing decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 04:37 AM