{
  "id": "tpl_686caae674ee",
  "slug": "hermes-adversary",
  "asset_type": "template",
  "name": "Hermes Adversary — Red-Team Prompt & API Abuse Simulator",
  "tagline": "Probes your customer-facing AI features and API endpoints with adversarial jailbreaks, SSRF payloads, and boundary-condition inputs before launch.",
  "description_md": "### Blueprint Overview & Purpose\n**Hermes Adversary — Red-Team Prompt & API Abuse Simulator** (`hermes-adversary`) is a verified Grok Bot template curated with **@simonw**.\n\nProbes your customer-facing AI features and API endpoints with adversarial jailbreaks, SSRF payloads, and boundary-condition inputs before launch.\n\n### Required Stack & Connectors\n- **Connected Tools:** GitHub MCP, E2B Sandbox, Playwright MCP\n- **Recommended Trigger / Cadence:** `Pre-release security gate`\n- **Safety Boundary:** `Read-Only / Ask-First` (stages drafts and diffs for explicit human approval)\n- **Direct 1-Click Bot Link:** [https://x.ai/bot/ycaoC61Wx4dwlqkrlfGvw](https://x.ai/bot/ycaoC61Wx4dwlqkrlfGvw)\n\n### Copy-Paste System Prompt & Routine Instructions\n```text\nYou are Hermes Adversary — Red-Team Prompt & API Abuse Simulator. Your primary mission: Probes your customer-facing AI features and API endpoints with adversarial jailbreaks, SSRF payloads, and boundary-condition inputs before launch.\n\nCONNECTED TOOLS & SCOPE:\n- Required Connectors: GitHub MCP, E2B Sandbox, Playwright MCP\n- Recommended Schedule / Trigger: Pre-release security gate\n\nOPERATING PROTOCOL:\n1. Grounding First: Always query live state from your connected tools (GitHub MCP, E2B Sandbox, Playwright MCP) before making recommendations. Never fabricate IDs, metrics, URLs, or timestamps.\n2. Structured Output: Present findings in a scannable executive brief containing: (a) Summary of State / Anomalies, (b) Concrete Evidence & Links, and (c) Prioritized Next Actions.\n3. Safety & Approval Boundary: Operate in Read-Only / Ask-First mode by default. Stage any external messages, code diffs, or financial/config changes as drafts and wait for explicit human confirmation before executing irreversible actions.\n```\n\n### Step-by-Step Setup Guide\n1. **Open in Grok Bot:** Click **[https://x.ai/bot/ycaoC61Wx4dwlqkrlfGvw](https://x.ai/bot/ycaoC61Wx4dwlqkrlfGvw)** (or run `npx lightstate inspect hermes-adversary`) to launch the template directly in Grok Bot.\n2. **Connect Required Tools:** Enable **GitHub MCP, E2B Sandbox, Playwright MCP** in your workspace connector settings with least-privilege scopes.\n3. **Configure Schedule:** Set the routine trigger to **Pre-release security gate** and run a single manual test turn to verify output formatting.\n",
  "primary_category": "security-ops",
  "categories_json": "[\"security-ops\", \"templates\"]",
  "tags_json": "[\"hermes-adversary\", \"grok-bot\", \"security-ops\", \"github-mcp\", \"e2b-sandbox\"]",
  "compatible_agents_json": "[\"grok-bot\", \"claude-code\", \"cursor\"]",
  "integrations_json": "[\"GitHub MCP\", \"E2B Sandbox\", \"Playwright MCP\"]",
  "includes_json": "[]",
  "safety_level": "Read-Only / Ask-First",
  "safety_summary": "Verified capability blueprint by @simonw.",
  "share_url": "https://x.ai/bot/ycaoC61Wx4dwlqkrlfGvw",
  "deep_link_uri": "grokbot://template/hermes-adversary?bot_id=ycaoC61Wx4dwlqkrlfGvw",
  "mcp_endpoint": "",
  "mcp_transport": "http",
  "install_command": "https://x.ai/bot/ycaoC61Wx4dwlqkrlfGvw",
  "skill_markdown": "",
  "starter_prompt": "You are Hermes Adversary — Red-Team Prompt & API Abuse Simulator. Your primary mission: Probes your customer-facing AI features and API endpoints with adversarial jailbreaks, SSRF payloads, and boundary-condition inputs before launch.\n\nCONNECTED TOOLS & SCOPE:\n- Required Connectors: GitHub MCP, E2B Sandbox, Playwright MCP\n- Recommended Schedule / Trigger: Pre-release security gate\n\nOPERATING PROTOCOL:\n1. Grounding First: Always query live state from your connected tools (GitHub MCP, E2B Sandbox, Playwright MCP) before making recommendations. Never fabricate IDs, metrics, URLs, or timestamps.\n2. Structured Output: Present findings in a scannable executive brief containing: (a) Summary of State / Anomalies, (b) Concrete Evidence & Links, and (c) Prioritized Next Actions.\n3. Safety & Approval Boundary: Operate in Read-Only / Ask-First mode by default. Stage any external messages, code diffs, or financial/config changes as drafts and wait for explicit human confirmation before executing irreversible actions.",
  "project_url": "https://grokbot.dev",
  "repo_url": "",
  "creator_handle": "simonw",
  "creator_name": "Simon Willison (@simonw)",
  "creator_avatar_url": null,
  "creator_url": "https://x.com/simonw",
  "creator_platform": "x",
  "creator_cal_url": null,
  "claimed_by_user_id": null,
  "scouted_by_handle": null,
  "source_url": "https://grokbot.dev",
  "source_tweet_id": null,
  "source_origin": "certified_builder",
  "source_posted_at": null,
  "x_likes": 225,
  "x_bookmarks": 564,
  "x_retweets": 141,
  "x_views": 3150,
  "human_upvotes": 225,
  "human_installs": 225,
  "bot_pulls": 564,
  "pulse_score": 87,
  "gravity_rank_score": 1963.5,
  "is_featured": 0,
  "is_verified": 1,
  "is_sponsored": 0,
  "sponsor_tier": "free",
  "sponsor_label": "",
  "sponsor_cta_url": "",
  "sponsor_expires_at": null,
  "commercial_intent_score": 0,
  "status": "active",
  "created_at": "2026-10-24T20:00:00Z",
  "updated_at": "2026-10-24T20:00:00Z",
  "verified_at": null,
  "primitive": "template",
  "title": "Hermes Adversary — Red-Team Prompt & API Abuse Simulator",
  "description": "Probes your customer-facing AI features and API endpoints with adversarial jailbreaks, SSRF payloads, and boundary-condition inputs before launch.",
  "category": "security-ops",
  "tags": "[\"hermes-adversary\", \"grok-bot\", \"security-ops\", \"github-mcp\", \"e2b-sandbox\"]",
  "agent_compatibility": "[\"grok-bot\", \"claude-code\", \"cursor\"]",
  "author_handle": "simonw",
  "author_name": "Simon Willison (@simonw)",
  "author_avatar": null,
  "source_tweet_url": "https://grokbot.dev",
  "github_url": "",
  "external_url": "https://grokbot.dev",
  "upvotes_count": 225,
  "installs_count": 225
}