performing-open-source-intelligence-gathering

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflows and scripts (notably scripts/process.py and scripts/agent.py) fetch and parse open/public third-party content — e.g., crt.sh, target websites' HTML/robots.txt/security.txt, Hunter.io, GitHub/paste sites, Google searches and breach databases — and then use that extracted data to drive findings and recommended attack actions, so untrusted user-generated content can materially influence agent decisions.