makecontents

Warn

Audited by Snyk on Mar 9, 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 fetches public RSS/RSSHub feeds via POST /news/fetch and GET /news/grouped?agent=1 and ingests the GET /news/agent-summary fields (saved_news, all_news_in_period) as part of its required learning, selection, and publishing workflows in SKILL.md, meaning untrusted third-party content can directly influence the agent's decisions and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 01:31 PM