maishou

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

• Third-party content exposure detected (low risk: 0.10). The workflow searches e-commerce listings and reads product titles, shop names, and details provided by third-party sellers on shopping platforms via API calls.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill makes API calls to an arbitrary and third-party remote server (maishou88.com) for operational search and detail retrieval, representing an unverified runtime external dependency with unknown provenance.