daily-briefing

Warn

Audited by Snyk on Feb 16, 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). This skill clearly ingests and summarizes untrusted third‑party content — e.g., "Twitter highlights" pulled from items, Exa searches for Substack/news, WebSearch for weather, and public APIs like CoinGecko — which the agent is expected to read and include in the briefing, creating a surface for indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 03:25 AM