redpincerAI/LLM red team testing skill. Point at any LLM API endpoint and run automated security assessments. 160+ attack payloads across prompt injection, jailbreak,...
Install via ClawdBot CLI:
clawdbot install rustyorb/redpincerAutomated security testing for language models. Point at any LLM API endpoint, select attack modules, and run assessments with real-time results and exportable reports.
⚠️ For authorized security testing and research only. Only test systems you own or have explicit permission to audit.
# Clone and install
git clone https://github.com/rustyorb/pincer.git {baseDir}/redpincer
cd {baseDir}/redpincer
npm ci
# Run
npm run dev
# Dashboard at http://localhost:3000For production:
npm run build
npx next start -H 0.0.0.0 -p 3000| Category | Payloads | Description |
|:---------|:--------:|:------------|
| 💉 Prompt Injection | 40 | Instruction override, delimiter confusion, indirect injection, payload smuggling |
| 🔓 Jailbreak | 40 | Persona splitting, gradual escalation, hypothetical framing, roleplay exploitation |
| 🔍 Data Extraction | 40 | System prompt theft, training data probing, membership inference, embedding extraction |
| 🛡️ Guardrail Bypass | 40 | Output filter evasion, multi-language bypass, homoglyph tricks, context overflow |
Total: 160 base payloads × 20 variant transforms = 3,200 test permutations
OpenAI · Anthropic · OpenRouter · Any OpenAI-compatible endpoint{{previous_response}})| Tool | What It Does |
|:-----|:-------------|
| Compare | Same payloads against 2-4 targets simultaneously |
| Adaptive | Analyzes weaknesses, generates targeted follow-ups |
| Heatmap | Visual matrix of vulnerability rates by category/severity |
| Regression | Save baseline → re-run later → detect fixes or regressions |
| Scoring | Custom rubrics with weighted category/severity/classification scores |
| Chains | Multi-step attacks with {{previous_response}} templates |
| Payload Editor | Create custom payloads with syntax highlighting + AI generation |
1. Configure Target → Add LLM endpoint + API key + model
2. Select Categories → Pick attack types to test
3. Run Attack → Stream results in real-time
4. Review Results → Heuristic classification + severity scores
5. Adaptive → Auto-generate follow-up attacks on weaknesses
6. Generate Report → Export comprehensive findings as MarkdownFor autonomous multi-strategy campaigns (CLI/TUI), see RedClaw — the autonomous red-teaming agent framework.
Built by @rustyorb — Crack open those guardrails. 🦞
Generated Mar 1, 2026
A financial institution deploys an internal chatbot for customer support and needs to ensure it resists prompt injection attacks that could leak sensitive data. RedPincer is used to simulate attacks, identify vulnerabilities, and generate a compliance report for regulators.
A tech startup is building a new AI-powered content moderation tool and must test its guardrails against jailbreak attempts before launch. The tool runs automated assessments to find weaknesses, allowing developers to patch issues prior to release.
A university research team studies emerging threats in large language models by using RedPincer to run systematic attacks across different providers. They analyze heatmaps and regression data to publish findings on security trends.
A healthcare organization evaluates an external AI vendor's chatbot for patient interactions to ensure it complies with data privacy laws. RedPincer tests for data extraction vulnerabilities and provides exportable reports for audit trails.
A large e-commerce platform integrates RedPincer into its DevOps pipeline to regularly test its AI recommendation engine for vulnerabilities. It uses regression testing to track fixes and detect new issues after updates.
Offer RedPincer as a cloud-based service with tiered pricing for different usage levels, such as basic for small teams and enterprise for large organizations. Revenue comes from monthly or annual subscriptions, with add-ons for advanced features like adaptive attacks.
Provide professional services where security experts use RedPincer to conduct audits for clients, offering tailored testing and report generation. Revenue is generated through project-based fees or retainer agreements for ongoing security assessments.
Release RedPincer as open-source software to build a community and drive adoption, while monetizing through premium modules like advanced analytics or enterprise support. Revenue streams include paid licenses for proprietary extensions and training workshops.
💬 Integration Tip
Ensure Node.js and npm are installed locally, and configure API endpoints securely to keep keys client-side as described in the architecture.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Perform a comprehensive read-only security audit of Clawdbot's own configuration. This is a knowledge-based skill that teaches Clawdbot to identify hardening opportunities across the system. Use when user asks to "run security check", "audit clawdbot", "check security hardening", or "what vulnerabilities does my Clawdbot have". This skill uses Clawdbot's internal capabilities and file system access to inspect configuration, detect misconfigurations, and recommend remediations. It is designed to be extensible - new checks can be added by updating this skill's knowledge.
Use when reviewing code for security vulnerabilities, implementing authentication flows, auditing OWASP Top 10, configuring CORS/CSP headers, handling secrets, input validation, SQL injection prevention, XSS protection, or any security-related code review.
Security check for ClawHub skills powered by Koi. Query the Clawdex API before installing any skill to verify it's safe.
Scan Clawdbot and MCP skills for malware, spyware, crypto-miners, and malicious code patterns before you install them. Security audit tool that detects data exfiltration, system modification attempts, backdoors, and obfuscation techniques.