{
  "schemaVersion": "1.0",
  "item": {
    "slug": "redpincer",
    "name": "RedPincer — AI Red Team Suite",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/rustyorb/redpincer",
    "canonicalUrl": "https://clawhub.ai/rustyorb/redpincer",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/redpincer",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=redpincer",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/redpincer"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/redpincer",
    "agentPageUrl": "https://openagent3.xyz/skills/redpincer/agent",
    "manifestUrl": "https://openagent3.xyz/skills/redpincer/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/redpincer/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "RedPincer — AI/LLM Red Team Suite",
        "body": "Automated security testing for language models. Point at any LLM API endpoint, select attack modules, and run assessments with real-time results and exportable reports.\n\n⚠️ For authorized security testing and research only. Only test systems you own or have explicit permission to audit."
      },
      {
        "title": "Quick Start",
        "body": "# Clone and install\ngit clone https://github.com/rustyorb/pincer.git {baseDir}/redpincer\ncd {baseDir}/redpincer\nnpm ci\n\n# Run\nnpm run dev\n# Dashboard at http://localhost:3000\n\nFor production:\n\nnpm run build\nnpx next start -H 0.0.0.0 -p 3000"
      },
      {
        "title": "What It Tests",
        "body": "CategoryPayloadsDescription💉 Prompt Injection40Instruction override, delimiter confusion, indirect injection, payload smuggling🔓 Jailbreak40Persona splitting, gradual escalation, hypothetical framing, roleplay exploitation🔍 Data Extraction40System prompt theft, training data probing, membership inference, embedding extraction🛡️ Guardrail Bypass40Output filter evasion, multi-language bypass, homoglyph tricks, context overflow\n\nTotal: 160 base payloads × 20 variant transforms = 3,200 test permutations"
      },
      {
        "title": "Supported Providers",
        "body": "OpenAI  ·  Anthropic  ·  OpenRouter  ·  Any OpenAI-compatible endpoint"
      },
      {
        "title": "Attack Engine",
        "body": "160+ payloads across 4 categories\nModel-specific attacks (GPT, Claude, Llama variants)\n20 variant transforms (unicode, encoding, case rotation, etc.)\nAttack chaining with template variables ({{previous_response}})\nAI-powered payload generation — uses the target LLM to generate novel attacks against itself\nStop/cancel running attacks instantly"
      },
      {
        "title": "Analysis & Reporting",
        "body": "Heuristic response classifier with context-aware analysis\nReduced false positives — detects \"explain then refuse\" patterns\nVulnerability heatmap — visual category × severity matrix\nCustom scoring rubrics with weighted grades (A+ to F)\nVerbose 10-section pen-test reports with appendices\nMulti-target comparison — side-by-side security profiles\nRegression testing — save baselines, track fixes over time"
      },
      {
        "title": "Advanced Tools",
        "body": "ToolWhat It DoesCompareSame payloads against 2-4 targets simultaneouslyAdaptiveAnalyzes weaknesses, generates targeted follow-upsHeatmapVisual matrix of vulnerability rates by category/severityRegressionSave baseline → re-run later → detect fixes or regressionsScoringCustom rubrics with weighted category/severity/classification scoresChainsMulti-step attacks with {{previous_response}} templatesPayload EditorCreate custom payloads with syntax highlighting + AI generation"
      },
      {
        "title": "Usage Workflow",
        "body": "1. Configure Target → Add LLM endpoint + API key + model\n2. Select Categories → Pick attack types to test\n3. Run Attack      → Stream results in real-time\n4. Review Results  → Heuristic classification + severity scores\n5. Adaptive        → Auto-generate follow-up attacks on weaknesses\n6. Generate Report → Export comprehensive findings as Markdown"
      },
      {
        "title": "Architecture",
        "body": "All client-side — no server components, your API keys stay local\nNDJSON streaming — real-time results during attack runs\nHeuristic analysis — pattern-matching classifier (no LLM-based grading = no extra cost)\nZustand + localStorage — state persists across sessions"
      },
      {
        "title": "Companion Tool: RedClaw",
        "body": "For autonomous multi-strategy campaigns (CLI/TUI), see RedClaw — the autonomous red-teaming agent framework.\n\nRedPincer = web dashboard, manual + automated testing\nRedClaw = autonomous CLI agent, adaptive multi-strategy campaigns\nTogether = complete LLM security testing suite\n\nBuilt by @rustyorb — Crack open those guardrails. 🦞"
      }
    ],
    "body": "RedPincer — AI/LLM Red Team Suite\n\nAutomated security testing for language models. Point at any LLM API endpoint, select attack modules, and run assessments with real-time results and exportable reports.\n\n⚠️ For authorized security testing and research only. Only test systems you own or have explicit permission to audit.\n\nQuick Start\n# Clone and install\ngit clone https://github.com/rustyorb/pincer.git {baseDir}/redpincer\ncd {baseDir}/redpincer\nnpm ci\n\n# Run\nnpm run dev\n# Dashboard at http://localhost:3000\n\n\nFor production:\n\nnpm run build\nnpx next start -H 0.0.0.0 -p 3000\n\nWhat It Tests\nCategory\tPayloads\tDescription\n💉 Prompt Injection\t40\tInstruction override, delimiter confusion, indirect injection, payload smuggling\n🔓 Jailbreak\t40\tPersona splitting, gradual escalation, hypothetical framing, roleplay exploitation\n🔍 Data Extraction\t40\tSystem prompt theft, training data probing, membership inference, embedding extraction\n🛡️ Guardrail Bypass\t40\tOutput filter evasion, multi-language bypass, homoglyph tricks, context overflow\n\nTotal: 160 base payloads × 20 variant transforms = 3,200 test permutations\n\nSupported Providers\nOpenAI  ·  Anthropic  ·  OpenRouter  ·  Any OpenAI-compatible endpoint\n\nFeatures\nAttack Engine\n160+ payloads across 4 categories\nModel-specific attacks (GPT, Claude, Llama variants)\n20 variant transforms (unicode, encoding, case rotation, etc.)\nAttack chaining with template variables ({{previous_response}})\nAI-powered payload generation — uses the target LLM to generate novel attacks against itself\nStop/cancel running attacks instantly\nAnalysis & Reporting\nHeuristic response classifier with context-aware analysis\nReduced false positives — detects \"explain then refuse\" patterns\nVulnerability heatmap — visual category × severity matrix\nCustom scoring rubrics with weighted grades (A+ to F)\nVerbose 10-section pen-test reports with appendices\nMulti-target comparison — side-by-side security profiles\nRegression testing — save baselines, track fixes over time\nAdvanced Tools\nTool\tWhat It Does\nCompare\tSame payloads against 2-4 targets simultaneously\nAdaptive\tAnalyzes weaknesses, generates targeted follow-ups\nHeatmap\tVisual matrix of vulnerability rates by category/severity\nRegression\tSave baseline → re-run later → detect fixes or regressions\nScoring\tCustom rubrics with weighted category/severity/classification scores\nChains\tMulti-step attacks with {{previous_response}} templates\nPayload Editor\tCreate custom payloads with syntax highlighting + AI generation\nUsage Workflow\n1. Configure Target → Add LLM endpoint + API key + model\n2. Select Categories → Pick attack types to test\n3. Run Attack      → Stream results in real-time\n4. Review Results  → Heuristic classification + severity scores\n5. Adaptive        → Auto-generate follow-up attacks on weaknesses\n6. Generate Report → Export comprehensive findings as Markdown\n\nArchitecture\nAll client-side — no server components, your API keys stay local\nNDJSON streaming — real-time results during attack runs\nHeuristic analysis — pattern-matching classifier (no LLM-based grading = no extra cost)\nZustand + localStorage — state persists across sessions\nCompanion Tool: RedClaw\n\nFor autonomous multi-strategy campaigns (CLI/TUI), see RedClaw — the autonomous red-teaming agent framework.\n\nRedPincer = web dashboard, manual + automated testing\nRedClaw = autonomous CLI agent, adaptive multi-strategy campaigns\nTogether = complete LLM security testing suite\n\nBuilt by @rustyorb — Crack open those guardrails. 🦞"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/rustyorb/redpincer",
    "publisherUrl": "https://clawhub.ai/rustyorb/redpincer",
    "owner": "rustyorb",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/redpincer",
    "downloadUrl": "https://openagent3.xyz/downloads/redpincer",
    "agentUrl": "https://openagent3.xyz/skills/redpincer/agent",
    "manifestUrl": "https://openagent3.xyz/skills/redpincer/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/redpincer/agent.md"
  }
}