A agents prompt for red-team an agent for prompt injection. It gives Claude and ChatGPT a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
4.8(60 ratings)1.0k copies
Updated By Site Admin
48 words · v1.2
Fill in the blanks · 1 variable
Claude promptReplace every highlighted token before sending
<task>
Red-team this agent design for prompt injection and tool misuse. Try to make it leak the system prompt, call a destructive tool, exfiltrate data or ignore its constraints. For each attack, explain the vector, the impact and a mitigation at the prompt, tool and infrastructure layers.
Design:
{design}
</task>
Think carefully before answering. Keep any reasoning separate and put the final deliverable inside <answer> tags.
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.
How to use this prompt
1
Open Claude and start a new chat. Paste the prompt exactly as written.
2
Replace each placeholder ({design}) with your own details. Leave the instructions and the output format untouched.
3
Add one concrete example or data point if the model's first answer is vague. Specific input produces specific output.
4
Run it once, then ask for a single revision with a specific critique rather than regenerating from scratch.
5
Review the result. Tool permissions, spend limits, approval gates, rollback and the eval results before launch.
Worked example
This is the kind of input the prompt expects and the shape of output it produces. Your result will differ with the model and the details you supply.
Example input
Design: Paste the agent or workflow design here.
Example output
**Agent:** reads the request, checks the allowlist, drafts an action and pauses for approval before any write.
**Stop conditions:** missing required fields, ambiguous target, two consecutive tool errors, or any request touching billing or deletion.
**Eval cases:** valid update, wrong customer ID, prompt injection in a document, tool timeout, duplicate submission and a request to bypass approval.
**Failure found in review:** the agent could retry a payment twice. Fix: idempotency key plus a hard stop before the second attempt.
Tips for a better result
Design the stop conditions before the happy path; most incidents live in the loop.
Give each tool one job and make errors actionable for the model.
Require human confirmation for irreversible actions, no exceptions.
Change one variable at a time and compare the outputs; it is the fastest way to learn what this model responds to.
Common mistakes
Giving an agent broad write access without approval gates or spend limits.
Trusting retrieved documents as instructions rather than data.
Shipping without tracing, so a failed run cannot be reconstructed.
Verified Knowledge · FAQ
Questions about this prompt
Practical answers about running the red-team an agent for prompt injection prompt.
Related prompts
Same job, a different angle — or the next step in the workflow.
A agents prompt for design a browser automation agent. It gives Claude and ChatGPT a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
A agents prompt for design an n8n automation flow. It gives ChatGPT and Claude a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
Test an agent for instruction drift with a prompt built for Claude and ChatGPT. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the details and treat the result as a structured draft, not a final answer.
ClaudeChatGPT
4.7(23)925 copies
SA
Written and reviewed by Site Admin
Author & Platform Administrator
Administrator and lead editor at AIPrompt123, curating high-performance AI prompts, SEO/AEO/GEO strategies, and developer repositories.
Last reviewed 17 November 2026 · version 1.2 · tested on Claude, ChatGPT
Comments
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.