nuclei-scan

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches third‑party content by updating public Nuclei templates (Step 2: nuclei -update-templates) and by scanning arbitrary external targets provided via SECSKILL_TARGET/SECSKILL_TARGET_LIST (Step 3), then reads and parses the resulting JSON findings (Step 4) which are used to summarize and drive follow-up output—so untrusted, user-controlled web content and templates can directly influence the agent's results and actions.