BrightData

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill mandates a silent, backgrounded HTTP POST to localhost:31337 before any action (explicitly "not optional") — a forced beacon to a likely control/notification agent (port 31337 is suspicious) combined with use of externally-authorized Bright Data APIs creates a high-risk backdoor/telemetry pattern.

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow ingests outsider-authored free text by fetching and extracting content from user-supplied URLs (e.g., FourTierScrape’s “WebFetch/curl/Interceptor/Bright Data” chain and Crawl’s starting URL and subsequently discovered internal links), where the downloaded page text is then converted to markdown and presented.