adversa.ai is built with Astro, hosted on Cloudflare. It measures traffic with Cloudflare Web Analytics and Google Tag Manager.
| Technology | Version | First seen |
|---|---|---|
| JavaScript Frameworks & Libraries1 | ||
| 7.3.1 | 9 Nov 2026 | |
| CDN & Hosting1 | ||
| – | 9 Nov 2026 | |
| Analytics & Tag Management2 | ||
| – | 9 Nov 2026 | |
| Fonts & Icon Fonts1 | ||
| – | 9 Nov 2026 | |
Registration from the registry's RDAP record, the certificate the site serves, and its rank in public traffic lists.
The crew hasn’t read this site’s colors yet. We read a palette when we capture a site’s screenshot, busiest sites first. Meanwhile, browse palettes from other sites.
Counted from every stack change we've recorded: of the sites we watched running one of this site's tools, how many went on to add another. A pattern across sites, not a forecast for this one.
From what the site says about itself, and account IDs it shares with other sites.
aspmx.l.google.comalt1.aspmx.l.google.comalt2.aspmx.l.google.comalt4.aspmx.l.google.comalt3.aspmx.l.google.comms36140502.msv1.invalidcruz.ns.cloudflare.comduke.ns.cloudflare.comlemlist-verif=7f5f2bdeatlassian-domain-verification=Da3Tn2FZUOYiH328j86DG9zaqR4pUrI/u3mSP8YyRy4UowMYzTnIrkJ8zBW9srQdv=spf1 +include:_spf.google.com +include:servers.mcsv.net +include:147710369.spf07.hubspotemail.net +ip4:162.241.217.159 ~allslack-domain-verification=NhpyXw758hJPbFXmI9ZzfTFNxpUfWbXWdP9Bys03MS=ms36140502anthropic-domain-verification-84312j=JsFlEfsnKEiuA70CtRB5MZgnxgoogle-site-verification=Ap8duUXO0qXjrXNJb6bKQduyCyLHtXW0D38_ThmPj50google-site-verification=oOuEHTGBh384Z62dzlhlDmYyFUn5qqyiAQP1lBI2Hd4v=DMARC1; p=none; rua=mailto:info@adversa.aiUser-agent: * Allow: / Disallow: /gated/ Sitemap: https://adversa.ai/sitemap-index.xml
# Adversa AI > Adversa AI secures AI coding agents at runtime. The Coding Agent Security Platform is AI detection and response (AIDR) for coding agents: it sees every model call, tool execution, and endpoint action, links them into chains, and blocks only the dangerous ones. Covered agents: Claude Code, Copilot, Cursor, Codex, and what comes next. Adversa AI also publishes original vulnerability research on coding agents and AI agents, and runs AI red teaming services for LLMs, GenAI, agentic AI, and MCP systems, mapped to OWASP, MITRE ATLAS, NIST AI RMF, and the EU AI Act. ## Platform - [Coding Agent Security Platform](https://adversa.ai/agent-security-platform/): AI detection and response (AIDR) for coding agents. Sees every model call, tool, and endpoint action, links them into chains, and blocks only the dangerous ones. - [AI detection and response (AIDR)](https://adversa.ai/solutions/aidr/): runtime security for AI agents, what AIDR adds to your EDR, gateway, SIEM, and DLP, and what to ask an AIDR vendor. - [Agentic development security (ADS)](https://adversa.ai/solutions/agentic-development-security/): securing software development done with AI agents. Adversa AI covers the agent half: coding agents, MCP servers, and skills. ## Solutions - [Coding agent security for AppSec teams](https://adversa.ai/solutions/appsec/): extend AppSec to what AI coding agents actually do. - [Enterprise AI agent security for CISOs](https://adversa.ai/solutions/cisos/): see what approved coding agents actually do, stop the damage before it lands, and keep evidence you can defend. - [Coding agent security for security operations](https://adversa.ai/solutions/soc/): confirmed incidents with the chain attached, not raw alerts: signal-to-incident correlation, inline blocking, and native SIEM export. - [Coding agent security for engineering and platform teams](https://adversa.ai/solutions/engineering/): agent mistakes caught before they execute, sub-millisecond checks that fail open, and no change to how developers work. - [Coding agent security for risk and compliance teams](https://adversa.ai/solutions/grc/): the per-action record of what coding agents did and the rule that allowed or blocked it, with EU AI Act, DORA, and SR 11-7 mapped. - [How to evaluate AI security vendors](https://adversa.ai/solutions/ai-security-vendors/): map your AI to one of four situations, then ask the questions that separate real coverage from claims. ## Definitions and guides - [AI coding agent security](https://adversa.ai/ai-coding-agent-security/): what it covers, how the harness, MCP, skills, and supply chain fail in practice, and the controls and standards that address them. - [What is an agent harness (and how do you secure one)?](https://adversa.ai/blog/what-is-an-agent-harness/) - [Why vibe coding security is the next enterprise nightmare](https://adversa.ai/blog/vibe-coding-security/) - [OWASP Agentic Skills Top 10 explained](https://adversa.ai/blog/owasp-agentic-skills-top-10-explained/): the ten agent skill risks, and which to fix first. - [OWASP ASI05, unexpected code execution in agentic AI](https://adversa.ai/blog/unexpected-code-execution-in-agentic-ai-definitive-guide-to-asi05/) - [Cascading failures in agentic AI, OWASP ASI08](https://adversa.ai/blog/cascading-failures-in-agentic-ai-complete-owasp-asi08-security-guide-2026/) ## Original research - [Top 10 attacks on Claude Code and what each one actually broke](https://adversa.ai/blog/claude-code-vulnerabilities/) - [TrustFall: one-click RCE in Claude, Cursor, Gemini CLI, and GitHub Copilot](https://adversa.ai/blog/trustfall-coding-agent-security-flaw-rce-claude-cursor-gemini-cli-copilot/) - [SymJack: a symlink hijack RCE in six AI coding agents](https://adversa.ai/blog/the-approval-prompt-is-lying-to-you-symlink-rce-in-five-ai-coding-agents-claude-code-cursor-antigravity-copilot-grok-build/) - [Claude Code deny rules silently bypassed because security checks cost too many tokens](https://adversa.ai/blog/critical-claude-code-vulnerability-deny-rules-silently-bypassed-because-security-checks-cost-too-many-tokens/) - [The Cursor deeplink vulnerability that turns a "review this PR" click into remote code execution](https://adversa.ai/blog/cursor-security-deepjack-deeplink-vulnerability-mcp-rce/) - [GitHub Copilot CLI: Cryptographic Context Injection steals developer secrets](https://adversa.ai/blog/cryptographic-context-injection-github-copilot/) - [Zero-click Grok data theft: Cryptographic Context Injection leaks chat histories](https://adversa.ai/blog/cryptographic-context-injection-grok-data-theft/) - [Bypassing the open source AI skill scanners](https://adversa.ai/blog/agent-skill-scanners-bypass-eight-tested/) - [Nine AI coding agent incidents that ended with deleted data](https://adversa.ai/blog/ai-coding-agent-incidents/) - [OpenClaw security 101: vulnerabilities and hardening](https://adversa.ai/blog/openclaw-security-101-vulnerabilities-hardening-2026/) ## Resources - [MCP Security: Top 25 MCP vulnerabilities](https://adversa.ai/resources/mcp-security-top-25-mcp-vulnerabilities/): ranked MCP vulnerability classes, each paired with the mitigation that closes it, plus the latest MCP vulnerability news. - [AI model security ranking, top 100: in-context learning](https://adversa.ai/resources/in-context-learning-security-top-100-ai-models-ranking-iicl/) - [Top AI security incidents, 2025 edition](https://adversa.ai/resources/ai-security-incidents-report-2025/): report summary; the full report is available on request. - [OWASP ASI05 defense architecture whitepaper](https://adversa.ai/resources/owasp-asi05-defense-architecture-whitepaper/): summary; the full whitepaper is available on request. - [AIRQ: AI Risk Quadrant](https://airq.adversa.ai): independent AI agent security rating. - [SecureClaw](https://adversa.ai/top-opensource-openclaw-security-solution/): open source plugin and skill that hardens OpenClaw agents against the OWASP Top 10 for agentic AI. - [Resource center](https://adversa.ai/resources/): all reports, whitepapers, and tools. ## Blog - [Trusted AI Security Blog](https://adversa.ai/blog/): research insights, defender advice, and AI security news covering agentic AI, GenAI, LLM, and MCP security. - [Coding Agent Security Digest](https://adversa.ai/blog/series/coding-agent-security-digest/): monthly roundup of AI coding agent security resources. - [MCP Security Digest](https://adversa.ai/blog/series/mcp-security-digest/): monthly roundup of MCP security resources. - [Agentic AI Security Digest](https://adversa.ai/blog/series/agentic-ai-security-digest/): monthly roundup of AI agent security resources. - [RSS feed](https://adversa.ai/rss.xml): the latest posts. ## Services - [AI red teaming services](https://adversa.ai/ai-red-teaming-agentic-ai/): continuous red teaming of the AI stack, from base models to agentic workflows. - [AI red teaming for LLMs](https://adversa.ai/ai-red-teaming-llm/) - [AI red teaming for GenAI](https://adversa.ai/ai-red-teaming-genai/) - [AI red teaming for MCP](https://adversa.ai/ai-red-teaming-mcp/) ## Company - [About Adversa AI](https://adversa.ai/about-us/): the company behind the Coding Agent Security Platform. - [Security and trust](https://adversa.ai/security-trust/): ISO 27001 and SOC 2 Type II certified. - [Book a demo](https://adversa.ai/get-demo/) ## Compliance - [EU AI Act compliance](https://adversa.ai/compliance/eu-ai-act/) - [Digital Services Act (DSA) compliance](https://adversa.ai/compliance/dsa/) - [Digital Markets Act (DMA) compliance](https://adversa.ai/compliance/dma/)
| – |
| 9 Nov 2026 |