continuous-hunter

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow ingests outsider-authored free text via the Recon Engine’s URL discovery/monitoring steps (e.g., katana/gau/waybackurls fetching arbitrary public web pages/URLs and extracting their readable content), which can then be included in LLM context for validation/reporting.