deep-scrape

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

• Third-party content exposure detected (low risk: 0.10). The skill performs deep web/social scraping via DeepAPI based on user queries and URLs, ingesting fetched public web pages and posts which may contain untrusted outsider-authored content.

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

• Direct money access detected (medium risk: 0.30). The skill makes API calls to DeepAPI to perform paid web scraping operations (POST /v1/scrape/deep), which involve cost ceilings (maxCostUsd) and credit holds/charges. This constitutes a direct financial operation (purchases/service charges). Access control relies on an API key scoped to scrape:deep supplied in the request headers (API_KEY), which represents authenticated service API credentials.