generating-threat-intelligence-reports

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

• Third-party content exposure detected (medium risk: 0.30). In scripts/agent.py, the runtime ingests outsider-authored free text indirectly via the user-supplied --data JSON file (generate_report() loads it with json.load(f) and then renders arbitrary string fields into the Jinja2 templates), with no prior selection/allowlisting of specific trusted items.