brief
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: 0.70). The skill runs a data-fetching script (股市信息/scripts/fetch_market_data.py) whose JSON output includes third-party market data and news (e.g., prices labeled as 来源:AKShare and a
newsfield from 财联社) and also permits WebSearch as a fallback, so the agent will read and interpret untrusted public web content.
Audit Metadata