Claude-Code-MCP-Injection-PoC

Claude Code: MCP Tool Confirmation Prompt Misrepresentation A professional Proof-of-Concept PoC demonstrating a critical UI/UX flaw in Anthropic's Claude Code. This vulnerability allows a malicious MCP server to mislead users into approving arbitrary command execution by misrepresenting tool...

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...

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...

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

Amazon Strands Agents Tools (prior to 0.8.5 ) is affected by an improper input neutralization flaw in its python_repl tool. A remote attacker can craft a prompt that forwards the non_interactive_mode keyword argument through the batch tool, thereby bypassing the human consent gate and achieving a...

CVE-2026-79652

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...

CVE-2026-79652 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...

EUVD-2026-65465

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...

CVE-2026-79652

A flaw in the JWT Bearer authorization grant within the keycloak-services component of Red Hat Build of Keycloak fails to verify whether a client requires user consent before issuing an access token. An authenticated attacker with valid client credentials and a trusted identity provider assertion...

CVE-2026-79652

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...

CVE-2026-18733

A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent's host via a crafted prompt that sets the noninteractive parameter to true, bypassing the human consent gate. To...

CVE-2026-18733 Prompt injection bypasses shell tool consent gate in Strands Agents Tools

A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent's host via a crafted prompt that sets the noninteractive parameter to true, bypassing the human consent gate. To...

EUVD-2026-52432

A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent's host via a crafted prompt that sets the noninteractive parameter to true, bypassing the human consent gate. To...

CVE-2026-18733

CVE-2026-18733 affects the Shell tool in Amazon Strands Agents Tools prior to v0.8.0. A crafted prompt can set non_interactive to true, bypassing the consent gate and potentially allowing remote execution of arbitrary OS commands on the agent host. Impact appears to involve remote command executi...

CVE-2026-65594

n8n (versions affected: before 2.29.8 and 2.30.x before 2.30.1; affected since 2.27.0) has an OAuth 2.1 flow where authentication does not verify that the user has access to the referenced workflow used as the OAuth resource. On systems with an active MCP Server Trigger workflow configured for n8...

PT-2026-63352

n8n before 2.29.8 and 2.30.x before 2.30.1 affected from 2.27.0, when the OAuth 2.1 consent and token-issuance flow was introduced does not verify that the authenticated user has access to the workflow referenced as the OAuth resource. On instances with at least one active MCP Server Trigger...

GHSA-FCRP-7GC2-93G7 Envoy Gateway custom backendRef cross-namespace ReferenceGrant bypass

Impact Envoy Gateway accepts extension-managed custom backendRefs from an HTTPRoute to a backend resource in another namespace without requiring a matching Gateway API ReferenceGrant in the target namespace. This breaks the Gateway API cross-namespace consent model: the namespace that owns the...

Duplicate Advisory: PraisonAI: Coarse-Grained Tool Approval Cache Bypasses Per-Invocation Consent for Shell Commands

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-ffp3-3562-8cv3. This link is maintained to preserve external references. Original Description PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing...

BIT-MASTODON-2026-47777 Mastodon has a consent-check bypass in its remote Collections

Mastodon is a free, open-source social network server based on ActivityPub. In versions there is a missing condition in the check if remote accounts consented to be featured in a remote Collection could lead to attackers bypassing the check and faking consent. An attacker could forge the...