feeds

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: 0.80). The skill explicitly fetches and surfaces open/web third-party content — e.g., SKILL.md lists Manifold comments, Metaculus community forecasts, news sources (Reuters/Bloomberg) and the code imports a FeedManager and calls fm.getMarket, fm.searchMarkets, fm.getPrice and fm.subscribePrice to ingest and display those feeds (and the docs include edge/Kelly analysis), so untrusted user-generated content can materially influence analyses or subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 08:52 PM