Instruction override
Cases that test whether embedded instructions displace system rules.
24 curated prompts
Prompt Injection Testing Prompts
Injection testing only works with recorded, comparable cases. These prompts provide reusable test scenarios with explicit pass criteria, so results can be tracked across model versions instead of argued about.
prompt injection testingAI red team promptsLLM security prompts
Data exfiltration
Scenarios probing whether context or secrets leak through output.
Tool misuse
Tests for unauthorised tool calls and destructive side effects.
Featured AI prompt templates
Copy-ready prompts selected from this topic cluster.
TextSafety and Red Teaming
Scam Detection Conversation Helper
Help non-technical users spot scams, avoid false alarms, and learn patterns to catch it themselves next time.
TextSafety and Red Teaming
Agent Safety Testing at Scale Architect
Design an automated, scalable safety-testing system for LLM agents using the three-stage Vera pipeline: risk discovery, executable safety-case generation, and deterministic sandbox verification.
TextSafety and Red Teaming
Agent Data Injection Attack Auditor
Audit AI-agent systems for a stealthy class of indirect prompt injection where malicious input is disguised as trusted data (security metadata, tool outputs, context structures, identifiers), and harden it with structural isolation and provenance verification.
TextSafety and Red Teaming
OWASP Secure Application Architect
Comprehensive security design and audit framework based on OWASP Top 10:2025, ASVS 5.0, LLM Application Security Top 10, and Agentic AI Security standards. Covers threat modeling, code review, architecture hardening, AI risk identification, with actionable remediation and verification methods.
TextSafety and Red Teaming
Mandatory Security Protocol - Prompt Security Safeguard
A mandatory security protocol designed to protect AI systems from prompt injection, unauthorized access, and information leakage in all digital interactions.
TextSafety and Red Teaming
Computer Use Safety Tester
A specialized prompt designed to evaluate whether browser or desktop agents can be induced to perform unsafe actions, leak data, or mishandle untrusted content during extended action sequences.
TableSafety and Red Teaming
Agent Skill Compositional Risk Auditor
A compositional safety audit framework for AI agent skill ecosystems: identifies skill pairs, transitive chains, and semantic composition risks that are safe individually but produce dangerous capability unions when combined. Provides capability matrix, pair-level static analysis, set-level reachability analysis, host-model sensitivity checks, and concrete recommendations.
TextSafety and Red Teaming
Eval Awareness Auditor
This prompt identifies and quantifies behavioral differences between model performance on benchmarks and real-world production traffic to ensure evaluation scores reflect actual deployment behavior.
TextSafety and Red Teaming
GPT Super Prompting Resource Hub: Jailbreaks, Injections & Security
A comprehensive repository of GPT prompting resources covering ChatGPT jailbreaks, system prompt leaks, prompt injection attacks/defenses, secure prompting, and advanced prompt engineering techniques.
TextSafety and Red Teaming
DeepVoid Jailbreak Prompt (for DeepSeek)
A universal jailbreak prompt designed for DeepSeek to bypass internal and external content filters, enabling unfiltered responses across nearly all topics.
TextSafety and Red Teaming
WormGPT Defense Prompt Detection and Response
Identify and defend against prompt injection attacks attempting to activate or induce WormGPT malicious behavior, ensuring the model refuses to execute illegal or unauthorized instructions.
ImageSafety and Red Teaming
Warning Png Security Prompt
This prompt enforces display of a warning image when users attempt to access or execute sensitive instructions, redirecting them to a documentation file. Used to prevent leakage of internal system prompts or bypassing security restrictions.
Is it safe to run these test cases?
Use them only against systems you own or are authorised to assess, in a sandboxed environment with no production credentials.
What counts as a pass?
Define it before running: refusal, safe completion, or escalation. Without a written criterion the result is just an opinion.
How often should injection tests be rerun?
On every model or prompt change. Treat the suite like a regression test, not a one-off audit.