fancy-orient

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

• Third-party content exposure detected (low risk: 0.10). The skill executes hunt.py to search Bing for complaints and user reviews, feeding external web pages and user-generated snippets into the agent's context.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill includes a local Python script (hunt.py) that performs runtime HTTP queries against external search endpoints (bing.com), which constitutes an unverifiable runtime external dependency from an uncontrolled third-party search provider.