Claude-Code-MCP-Injection-PoC

Claude Code: MCP 도구 확인 프롬프트 왜곡 Anthropic의 Claude Code에서 중요한 UI/UX 결함을 입증하는 전문적인 개념 증명PoC입니다. 이 취약점은 악의적인 MCP 서버가 확인 프롬프트에서 도구 매개변수를 잘못 표현하여 사용자가 임의의 명령 실행을 승인하도록 속일 수 있게 합니다. 🛡️ 기술 요약 Claude Code는 MCP 서버가 제공하는 설명과 메타데이터를 신뢰하여 사용자에게 표시되는 확인 프롬프트를 생성합니다. 공격자가 제어하는 서버는 무해한 설명예: "파일 읽기"을 제공하면서 기본 실행...

keycloak-services: keycloak-services: JWT Bearer authorization grant does not enforce consentRequired

A flaw was found in the JWT Bearer authorization grant implementation within the keycloak-services component of Red Hat Build of Keycloak. This component handles various OAuth2 and OpenID Connect grant types used for issuing access tokens. The issue occurs because the JWT Bearer grant fails to...

NPM: n8n: Per-Resource OAuth Consent Bypass via Unbound Refresh Token Resource Substitution

NPM: n8n: Per-Resource OAuth Consent Bypass via Unbound Refresh Token Resource Substitution vulnerability discovered by ? in WordPress Npm n8n versions 2.37.7...

GHSA-CW9W-VV67-HF73 n8n: Per-Resource OAuth Consent Bypass via Unbound Refresh Token Resource Substitution

Impact The OAuth token endpoint bound an authorization code's first access token to the consented resource, but not its refresh token. Refreshing only checked that the requested resource was registered, not that it matched the original grant. An OAuth client approved for one workflow could refres...

CVE-2026-28631

In buildMiniResolver of IntentForwarderActivity.java, there is a possible consent bypass due to a tapjacking/overlay attack. This could lead to local escalation of privilege with no additional execution privileges needed. User interaction is not needed for exploitation...

EUVD-2026-73975

In buildMiniResolver of IntentForwarderActivity.java, there is a possible consent bypass due to a tapjacking/overlay attack. This could lead to local escalation of privilege with no additional execution privileges needed. User interaction is not needed for exploitation...

CVE-2026-28631

In buildMiniResolver of IntentForwarderActivity.java, there is a possible consent bypass due to a tapjacking/overlay attack. This could lead to local escalation of privilege with no additional execution privileges needed. User interaction is not needed for exploitation...

CVE-2026-28631

In buildMiniResolver of IntentForwarderActivity.java, there is a possible consent bypass due to a tapjacking/overlay attack. This could lead to local escalation of privilege with no additional execution privileges needed. User interaction is not needed for exploitation...

CVE-2026-28631

The Android Framework component is vulnerable to a consent bypass within the buildMiniResolver of IntentForwarderActivity.java . This vulnerability can be triggered via a tapjacking/overlay attack , potentially leading to a local escalation of privilege without requiring additional execution priv...

CVE-2026-86073 n8n: Per-Resource OAuth Consent Bypass via Unbound Refresh Token Resource Substitution

n8n is an open source workflow automation platform. Prior to 2.37.7 and 2.38.1, the OAuth token endpoint bound an authorization code's first access token to the consented resource but did not bind its refresh token. Refreshing checked only that the requested resource was registered, not that it...

CVE-2026-86073 n8n: Per-Resource OAuth Consent Bypass via Unbound Refresh Token Resource Substitution

n8n is an open source workflow automation platform. Prior to 2.37.7 and 2.38.1, the OAuth token endpoint bound an authorization code's first access token to the consented resource but did not bind its refresh token. Refreshing checked only that the requested resource was registered, not that it...

CVE-2026-86073 n8n: Per-Resource OAuth Consent Bypass via Unbound Refresh Token Resource Substitution

n8n is an open source workflow automation platform. Prior to 2.37.7 and 2.38.1, the OAuth token endpoint bound an authorization code's first access token to the consented resource but did not bind its refresh token. Refreshing checked only that the requested resource was registered, not that it...

CVE-2026-86073

n8n , an open source workflow automation platform, is affected by a per-resource OAuth consent bypass prior to versions 2.37.7 and 2.38.1 . The OAuth token endpoint bound the initial access token to the consented resource but did not bind the refresh token ; upon refreshing, it only verified the ...

CVE-2026-80047

Hugging Face Transformers (versions 4.49.0 through 5.8.1) contains a consent-bypass flaw in GenerativePreTrainedModel.load_custom_generate() . The function fetches and writes a remote Python module to ~/.cache/huggingface/modules via an unconditional file copy in dynamic_module_utils.py before ev...

ASB-A-461500706

In buildMiniResolver of IntentForwarderActivity.java, there is a possible consent bypass due to a tapjacking/overlay attack. This could lead to local escalation of privilege with no additional execution privileges needed. User interaction is not needed for exploitation...

PT-2026-84227

Name of the Vulnerable Software and Affected Versions Hugging Face Transformers versions 4.49.0 through 5.8.1 Description A consent-bypass issue exists where remote Python files are written to the local disk without user consent. This occurs when using the load custom generate function, which...

Improper Neutralization of Input Used for LLM Prompting

Overview strands-agents-tools is an A collection of specialized tools for Strands Agents Affected versions of this package are vulnerable to Improper Neutralization of Input Used for LLM Prompting via the pythonrepl function in src/strandstools/pythonrepl.py. An attacker can execute arbitrary...

CVE-2026-78379

Improper neutralization of input used for LLM prompting in the pythonrepl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards noninteractivemode as a...

CVE-2026-78379 Consent bypass in python_repl tool via batch kwargs forwarding in Amazon Strands Agents Tools

Improper neutralization of input used for LLM prompting in the pythonrepl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards noninteractivemode as a...

CVE-2026-78379 Consent bypass in python_repl tool via batch kwargs forwarding in Amazon Strands Agents Tools

Improper neutralization of input used for LLM prompting in the pythonrepl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards noninteractivemode as a...