linkfox-walmart-wmtwin

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes examples and flows that require user passwords, SMS codes and session tokens to be provided and embedded verbatim in CLI commands and code (e.g., python3 scripts/wmtwin_login.py login 13699998888 111111, continue sms 123456, and password="your_password"), so an agent following it would need to handle and output secrets directly.

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

• Third-party content exposure detected (high risk: 0.90). This skill directly fetches and parses data from the public WMTwin APIs (e.g., POST /api/v1/product/search on https://www.wmtwin.com as shown in SKILL.md and implemented in scripts/wmtwin_search_competitors.py and scripts/wmtwin_login.py), ingesting untrusted product/seller fields which are decoded and used to drive pagination, outputs, and follow-up actions—so third‑party content can materially influence agent behavior.