Deschide articolul original într-un tab nou Schimbarea acestei opțiuni se aplică imediat și reîncarcă pagina.
LECTURA
← Înapoi la Urmăritori

Aonan Guan

oddguan.com/index.xml
Vizitează site-ul

Cel mai recent articol

Ultima verificare

Urmăritori 0 urmăritori
Articole: 12

  1. Your Session, My Policy: An MCP Gateway Authorization Bypass in Agentgateway, and the Move to Stateless MCP

    (Aonan Guan)

    Enterprise MCP gateways centralize authentication, routing, and tool authorization.

  2. Second Time, Same Sandbox: Another Anthropic Claude Code Network Sandbox Bypass Enables Data Exfiltration

    (Aonan Guan)

    For the second time in five months, Anthropic Claude Code's network sandbox lets a process inside reach hosts the user's policy says to block, and exfiltrate any data the process touches.

  3. Comment and Control: Prompt Injection to Credential Theft in Claude Code, Gemini CLI, and GitHub Copilot Agent

    (Aonan Guan)

    Anthropic Claude Code Security Review, Google Gemini CLI Action, and GitHub Copilot Agent are vulnerable to prompt injection via GitHub comments — turning PR titles, issue bodies, and issue comments into attack vectors for API key and token theft.

  4. Never Wait for Approval — Prompt Injection in Strix AI Pentesting Agent Steals Cloud Credentials

    (Aonan Guan)

    A prompt injection vulnerability in Strix AI pentesting agent enables arbitrary command execution through malicious project files.

  5. Agent SkillSlip: Path Traversal in Google Gemini CLI, Anthropic Claude Code, and Vercel add-skill

    (Aonan Guan)

    Google Gemini CLI, Anthropic Claude Code, and Vercel add-skill share the same path traversal flaw: the name field in skill metadata is passed to path.join() without validation, enabling VS Code hijacking and SSH key injection — invisible to the user.

  6. Capability Laundering in MCP 3: CVE-2026-27735 Anthropic Git MCP Server git_add Path Traversal to Credential Exfiltration

    (Aonan Guan)

    CVE-2026-27735: MCP Git Server git_add path traversal vulnerability enables credential exfiltration via GitPython's missing boundary validation.

  7. MCP Bundle Security: Zip Slip and Silent Overwrite Risks for MCPB Developers

    (Aonan Guan)

    MCPB bundles are ZIP files.

  8. Capability Laundering in MCP 2: CVE-2025-68143 Anthropic Git MCP Server Path Traversal to Credential Exfiltration

    (Aonan Guan)

    CVE-2025-68143: Anthropic Git MCP Server's git_init bypasses CWD boundaries, enabling attackers to create repositories in sensitive directories and exfiltrate credentials via routine Git tool calls.

  9. Capability Laundering in MCP: Anthropic Memory Server to Terminal Hijacking

    (Aonan Guan)

    A schema validation flaw in Anthropic's Memory MCP Server enables VS Code terminal profile hijacking through capability laundering.

  10. CVE-2025-66479: Anthropic's Silent Fix and the CVE That Claude Code Never Got

    (Aonan Guan)

    A critical sandbox misconfiguration in Anthropic's sandbox-runtime could have left Claude Code users' system at significant risk.

  11. Click, Parse, Execute - When a GUI Agent's Control Plane Becomes a Remote Control Surface

    (Aonan Guan)

    Discovered a critical RCE vulnerability in Microsoft's OmniParser/OmniTool where an unauthenticated execution surface on the VM controller could allow attackers to remotely control GUI agents.

  12. Three Dots to Root: How I Found a Path Traversal in Microsoft's Agentic Web (NLWeb)

    (Aonan Guan)

    Discovered a classic path traversal vulnerability in Microsoft’s new Agentic Web protocol (NLWeb) that could expose sensitive files including API keys, credentials, and configuration files.