morning-briefing

Warn

Audited by Snyk on Feb 15, 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). The skill explicitly aggregates sentiment from "60+ 财经 YouTuber" and instructs calling tools like list_tickers and get_ticker_sentiment to ingest and interpret public YouTuber/user-generated content (YouTube videos/posts) as part of its workflow, exposing the agent to untrusted third-party input.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:38 PM