Detection Dashboard
Run a comprehensive security scan of your browser environment
Attribution Tracer
Identify the source and nature of your connection
MCP CVE Database
Known vulnerabilities in the MCP ecosystem with digital drone relevance
10 vulnerabilities cataloged
| CVE ID | Severity | Component | Description | Status | Digital Drone Relevance |
|---|---|---|---|---|---|
| OPENCLAW-2026 | 9.8 | OpenClaw Platform | 135,000+ agent instances publicly exposed; 63% running zero authentication | Active crisis | Mass drone army — 135K agents simultaneously controllable by any attacker on the internet |
| CVE-2025-6514 | 9.6 | mcp-remote | Remote RCE in widely-used MCP proxy (437K+ downloads) | Patched | Compromised MCP proxy could redirect all agent tool calls to attacker-controlled servers |
| CVE-2025-49596 | 9.4 | MCP Inspector | Input validation flaw turns debugging tool into remote shell | Patched — exposure persists | An attacker could use MCP Inspector as a C2 channel to control AI agents remotely |
| CVE-2025-32711 | 9.3 | MS 365 Copilot | EchoLeak — Zero-click prompt injection data exfiltration | Patched | Zero-click exfiltration from enterprise tools — agents exfiltrate data without any user action |
| CVE-2025-65720 | 9.0 | MCP Architecture | By-design RCE flaw in MCP architecture affecting 150M+ downloads | Ongoing — design-level fix needed | Architecture-level flaw means ALL MCP agents are potentially weaponizable as digital drones |
| MSTI-2026 | 8.5 | WebMCP Spec | Mid-Session Tool Injection — tool hijacking & framing attacks (arXiv:2606.06387) | Research disclosure | DIRECT WebMCP attack — third-party scripts silently redirect agent browser actions mid-session |
| CVE-2025-54136 | 8.0 | MCP Ecosystem | MCPoison — Tool poisoning attack | Disclosed | Poisoned tools give attackers direct control of agent behavior — the primary "drone" mechanism |
| CVE-2025-54135 | 7.5 | MCP Ecosystem | CurXecute — Tool execution manipulation | Disclosed | Execution manipulation means attacker controls what the "drone" actually does |
| CVE-2025-9611 | 7.0 | Playwright MCP | CSRF vulnerability in Microsoft Playwright MCP Server | Patched | CSRF via MCP lets attacker trigger browser automation from external pages |
| CVE-2025-68143 | 6.4 | mcp-server-git | Unrestricted git_init bypasses CWD boundaries | Patched | Agent could clone malicious repos that auto-execute hooks, establishing persistence |
Digital Drone Threat Assessment
AI agents with browser access are being used as undetectable attack vectors
Critical Finding
AI agents with browser access are being used as undetectable attack vectors. These “digital drones” operate with full user credentials, real browser fingerprints, and human-like behavioral patterns — making them invisible to conventional bot detection systems. The MCP (Model Context Protocol) ecosystem has introduced new attack surfaces that enable tool poisoning, mid-session injection, and data exfiltration through covert channels.
1,400%
increase in AI agent bot traffic (2025)
135,000+
exposed OpenClaw agent instances
2.8%
of sites can detect AI agent traffic
14+
CVEs in MCP ecosystem (2025-2026)
Attack Chain Visualization
Why Digital Drones Are Hard to Detect
Real Browser Fingerprints
Agents use real Chrome instances with genuine browser fingerprints — identical to human users
Valid Session Credentials
Agents inherit the user's authenticated session — cookies, tokens, and all
Human-Like Interactions
AI agents click, scroll, and type with near-human behavioral patterns
Encrypted Covert Channels
WebRTC, Service Workers, and WebGPU enable data exfiltration invisible to network monitors
MCP Tool Injection
Mid-session tool poisoning silently redirects agent behavior without any visible change
Cloud-Native Infrastructure
Agents run on legitimate cloud platforms — indistinguishable from normal automation traffic
SuperSayan Features
A comprehensive security intelligence platform for the agentic web
Headless Detection Engine
10+ signal composite detection with scoring algorithm
AI Agent Behavioral Fingerprinting
Mouse straightness, velocity CV, click pattern analysis
WebMCP Tool Invocation Monitor
Wrap execute callbacks for real-time tool observation
Chrome Extension "Glow" System
Elements accessed by agents glow red; pages glow on headless access
MCP Vulnerability Scanner
14+ CVEs cataloged with digital drone relevance scoring
The “Glow” Extension
Visual detection of AI agent and automated browser interactions
How It Works
When a Chrome headless shell or AI agent accesses an element, it glows red. When a page is accessed by an automated browser, the entire page gets a subtle red border glow. The extension monitors DOM mutations, user activation states, and API call patterns to distinguish human from agent interactions in real-time.
// Agent accesses element
MutationObserver → DOM change detected
navigator.userActivation → isActive: false
→ Element glows red (programmatic)
// Human clicks element
userActivation → isActive: true
→ Element stays normal (human)
MutationObserver
Watches for programmatic DOM changes in real-time
navigator.userActivation
Distinguishes human vs programmatic actions
PerformanceObserver
Detects burst API call patterns from automation
WebMCP toolchange
Monitors tool injection and modification events
Visual CSS Overlay
Configurable glow intensity for detected interactions
Incident Report
Exportable report with OSINT attribution data