multi-wordcheck

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

• Third-party content exposure detected (low risk: 0.10). The workflow accepts arbitrary web URLs via user input and scrapes their content using extract_text.py, exposing the agent to outsider-authored text from fetched web pages.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill utilizes an operational remote API at redfox.hk for sensitive word checking, which is a third-party commercial service with unknown or arbitrary publisher provenance, categorizing it as high.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 0.70). The skill's documented workflow includes interacting with an external API service for sensitive word checks and handling credit exhaustion by invoking a recharge flow via Alipay (opening cashier URLs and polling payment status). Operating a payment recharge flow to fund API credits constitutes a direct financial operation. Because the documentation does not establish any qualifying independent access control or verification mechanism on the payment execution path itself, the financial-security exposure is classified as high.