news

Warn

Audited by Snyk on Feb 20, 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 ingests public third-party content — SKILL.md lists Twitter/X accounts and RSS feeds as "News Sources" and index.ts calls createNewsFeed/start() with those Twitter accounts — and it parses and auto-matches that content to drive market correlations, so untrusted user-generated posts could materially influence agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 08:52 PM