maimai-hub

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and scripts/maimai.py explicitly fetch and scrape user-generated content from the public site maimai.cn (API endpoints and fallback browser navigation to https://maimai.cn/company/gossip_discuss?webcid=...) and then reads and summarizes those posts as part of its workflow, exposing the agent to untrusted third‑party content that could carry injected instructions.