passive-recon

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

• Third-party content exposure detected (high risk: 0.85). At runtime the skill fetches outsider-authored public web content (e.g., crt.sh JSON, Wayback CDX JSON, HackerTarget/CIRCL API responses, ipapi.co JSON) via requests.get(...) and resp.json()/resp.text, which becomes readable text/structured data included in the agent’s LLM context through the pipeline’s printed/returned results.