fullscan

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow (Phase 1 Recon and Phase 2 js-analyzer / scanning steps) explicitly directs agents to discover and fetch content from target web assets and JS files for $ARGUMENTS (external domains), which are untrusted third‑party pages/files that the agents must read and that drive follow-on testing decisions.