opennews

Warn

Audited by Snyk on Apr 10, 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.md shows the agent calls the OpenNews API (e.g., POST /open/news_search and GET /open/free_hot) to fetch headlines, article text and social posts (Twitter/X, Telegram, public news sites) from public/untrusted sources and those items (news, tweets, AI-derived signals) are read and used in workflows and filtering (e.g., high-impact news, trading signals), so third‑party content can materially influence agent decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 10, 2026, 10:11 AM
Issues
1