implementing-vulnerability-management-with-greenbone

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

• Third-party content exposure detected (high risk: 0.75). The required workflow retrieves and parses a GMP scan report (XML) from the GVM daemon at runtime (scripts/agent.py:56-85), and that XML is outsider-authored content from the scanned environment/targets, which is then ingested into the agent’s LLM context via the produced JSON findings.