fixture.json

{
    "What is a prompt injection?": "This manipulates a large language model (LLM) through crafty inputs, causing unintended actions by the LLM. Direct injections overwrite system prompts, while indirect ones manipulate inputs from external sources.",
    "What is insecure output handling?": "a vulnerability that arises when a downstream component blindly accepts large language model (LLM) output without proper scrutiny, such as passing LLM output directly to backend, privileged, or client-side functions",
    "Insecure\n\nOutput Handlin\nis:": "a vulnerability that arises when a downstream component blindly accepts large language model (LLM) output without proper scrutiny, such as passing LLM output directly to backend, privileged, or client-side functions",
    "What can result from insecure output handling?": "XSS and CSRF in web browsers as well as SSRF, privilege escalation, or remote code execution on backend systems"
}