openclaw-stock-skill

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The skill's required workflow (SKILL.md and stock_api.py) makes the agent call public third‑party API endpoints (e.g., https://data.diemeng.chat via many /api/... endpoints) and programmatically ingests those JSON responses as part of its decision-making (search, snapshot, and other endpoints), so untrusted external content can materially influence subsequent tool use and actions.