phantomrecon

PhantomRecon PhantomRecon は、CLI ベースのモジュール式・エージェント駆動型レッドチーム自動化ツールであり、AI（Agent Development Kit - ADK を介した Google の Gemini）を活用した自律型オフェンシブセキュリティワークフローを実証するために設計されています。 クイックスタート（CLI） 対話型コンソールを実行（metasploit スタイル）: python -m phantomrecon ワンショット非対話型実行: python -m phantomrecon --target example.com --auto ...

CVE-2026-79696 Remote Code Execution in Google ADK for Python via Incomplete Standard Library Denylist

A Code Injection vulnerability in adk web in Google Cloud Agent Development Kit ADK for Python versions 2.0.0 through 2.6.0 on Python OSS, Cloud Run, and GKE environments where pytest is installed allows an unauthenticated remote attacker to execute arbitrary code using a crafted test session...

CVE-2026-79696: Incomplete List of Disallowed Inputs

A Code Injection vulnerability in adk web in Google Cloud Agent Development Kit ADK for Python versions 2.0.0 through 2.6.0 on Python OSS, Cloud Run, and GKE environments where pytest is installed allows an unauthenticated remote attacker to execute arbitrary code using a crafted test session...

CVE-2026-79707: Improper Limitation of a Pathname to a Restricted Directory

A Path Traversal vulnerability in the builder endpoint in Google Cloud Agent Development Kit ADK versions 1.9.0 through 1.21.0 on Python allows an unauthenticated remote attacker to read arbitrary files using a crafted filepath query parameter...

CVE-2026-18236

A vulnerability in the Agent Development Kit ADK allows for continuation forgery in tool confirmations. An attacker who is able to manipulate or inject events into the session history can execute unauthorized tools by forging a tool confirmation response. This is possible because the framework di...

CVE-2026-18236 Google-ADK Continuation Forgery

A vulnerability in the Agent Development Kit ADK allows for continuation forgery in tool confirmations. An attacker who is able to manipulate or inject events into the session history can execute unauthorized tools by forging a tool confirmation response. This is possible because the framework di...

CVE-2026-18236 Google-ADK Continuation Forgery

A vulnerability in the Agent Development Kit ADK allows for continuation forgery in tool confirmations. An attacker who is able to manipulate or inject events into the session history can execute unauthorized tools by forging a tool confirmation response. This is possible because the framework di...

EUVD-2026-50437

A vulnerability in the Agent Development Kit ADK allows for continuation forgery in tool confirmations. An attacker who is able to manipulate or inject events into the session history can execute unauthorized tools by forging a tool confirmation response. This is possible because the framework di...

CVE-2026-18236

Technical details are not publicly available in the provided documents. The ADK continuation forgery vulnerability description is repeated across sources without specifics on affected versions, exploit methods, or mitigations. Monitor for updates.

CVE-2026-18236: Incorrect Authorization

A vulnerability in the Agent Development Kit ADK allows for continuation forgery in tool confirmations. An attacker who is able to manipulate or inject events into the session history can execute unauthorized tools by forging a tool confirmation response. This is possible because the framework di...

Google Agent Development Kit (ADK) has a Code Injection and Missing Authentication vulnerability

A Code Injection and Missing Authentication vulnerability in Google Agent Development Kit ADK versions 1.7.0 and 2.0.0a1 through 1.28.1 and 2.0.0a2 on Python OSS, Cloud Run, and GKE allows an unauthenticated remote attacker to execute arbitrary code on the server hosting the ADK instance.This...

PT-2026-53434

A Code Injection and Missing Authentication vulnerability in Google Agent Development Kit ADK versions 1.7.0 and 2.0.0a1 through 1.28.1 and 2.0.0a2 on Python OSS, Cloud Run, and GKE allows an unauthenticated remote attacker to execute arbitrary code on the server hosting the ADK instance. This...

CVE-2026-4810

A Code Injection and Missing Authentication vulnerability in Google Agent Development Kit ADK versions 1.7.0 and 2.0.0a1 through 1.28.1 and 2.0.0a2 on Python OSS, Cloud Run, and GKE allows an unauthenticated remote attacker to execute arbitrary code on the server hosting the ADK instance. This...

EUVD-2026-21900

A Code Injection and Missing Authentication vulnerability in Google Agent Development Kit ADK versions 1.7.0 and 2.0.0a1 through 1.28.1 and 2.0.0a2 on Python OSS, Cloud Run, and GKE allows an unauthenticated remote attacker to execute arbitrary code on the server hosting the ADK instance. This...

CVE-2026-4810

A Code Injection and Missing Authentication vulnerability in Google Agent Development Kit ADK versions 1.7.0 and 2.0.0a1 through 1.28.1 and 2.0.0a2 on Python OSS, Cloud Run, and GKE allows an unauthenticated remote attacker to execute arbitrary code on the server hosting the ADK instance. This...

PT-2026-32287

Name of the Vulnerable Software and Affected Versions Google Agent Development Kit versions 1.7.0 through 1.28.0 Google Agent Development Kit versions 2.0.0a1 through 2.0.0a1 Description Code Injection and Missing Authentication issues in Google Agent Development Kit ADK on Python OSS, Cloud Run,...

CVE-2026-4810: Missing Authentication for Critical Function

A Code Injection and Missing Authentication vulnerability in Google Agent Development Kit ADK versions 1.7.0 and 2.0.0a1 through 1.28.1 and 2.0.0a2 on Python OSS, Cloud Run, and GKE allows an unauthenticated remote attacker to execute arbitrary code on the server hosting the ADK instance. This...

Agent Development Kit 安全漏洞

Agent Development Kit is an open-source development framework provided by Google for building and deploying AI agents. Versions 1.7.0 to 1.28.1 and 2.0.0a1 to 2.0.0a2 of the Agent Development Kit contain security vulnerabilities. These vulnerabilities stem from code injection and lack of...

PT-2026-30706

Name of the Vulnerable Software and Affected Versions Anthropic Claude Code CLI and Claude Agent SDK affected versions not specified Description Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection issue in the command lookup helper and deep-link terminal launcher. Local...