PromptInjection.qhelp

<!DOCTYPE qhelp PUBLIC
  "-//Semmle//qhelp//EN"
  "qhelp.dtd">
<qhelp>

<overview>
<p>Prompts can be constructed to bypass the original purposes of an agent and lead to sensitive data leak or 
operations that were not intended.</p>
</overview>

<recommendation>
<p>Sanitize user input and also avoid using user input in developer or system level prompts.</p>
</recommendation>

<example>
<p>In the following examples, the cases marked GOOD show secure prompt construction; whereas in the case marked BAD they may be susceptible to prompt injection.</p>
<sample src="examples/example.py" />
</example>

<references>
<li>OpenAI: <a href="https://openai.github.io/openai-guardrails-python">Guardrails</a>.</li>
</references>

</qhelp>