30 matches found
CVE-2026-5029-Exploit
🔥 CVE-2026-5029 — Code Runner MCP Server RCE Unauthenticated Remote Code Execution via the run-code MCP Tool Proof of Concept exploit for CVE-2026-5029 — a critical unauthenticated Remote Code Execution vulnerability in Code Runner MCP Server, triggered via the MCP tool when the server is run wit...
Symlink Attack
Overview @anthropic-ai/claude-code is an Use Claude, Anthropic's AI assistant, right from your terminal. Claude can understand your codebase, edit files, run terminal commands, and handle entire workflows for you. Affected versions of this package are vulnerable to Symlink Attack in the handling ...
Insecure Temporary File
Overview @anthropic-ai/claude-code is an Use Claude, Anthropic's AI assistant, right from your terminal. Claude can understand your codebase, edit files, run terminal commands, and handle entire workflows for you. Affected versions of this package are vulnerable to Insecure Temporary File via the...
Security Bulletin: Unauthenticated Server-Side RCE via PythonCodeStructuredTool in Public Flows
Summary Langflow OSS contains unauthenticated server-side RCE via PythonCodeStructuredTool executing attacker-controlled Python through exec at flow-build time. Sink in execself.toolcode, globals, localnamespace where toolcode is attacker-controlled template field. Two paths: A Authenticated POST...
PT-2026-61774
Name of the Vulnerable Software and Affected Versions praisonai-agents affected versions not specified Description The execute code tool contains a flaw in its subprocess sandbox that allows an arbitrary read primitive over blocklisted attributes. The issue arises from the combination of two...
CVE-2026-9368
A vulnerability was identified in NousResearch hermes-agent up to 2026.4.16. This impacts the function executecode of the file tools/codeexecutiontool.py of the component Environment Variable Handler. Such manipulation leads to sandbox issue. It is possible to launch the attack remotely. The...
EUVD-2026-31582
A vulnerability was identified in NousResearch hermes-agent up to 2026.4.16. This impacts the function executecode of the file tools/codeexecutiontool.py of the component Environment Variable Handler. Such manipulation leads to sandbox issue. It is possible to launch the attack remotely. The...
Malicious code in code-tool-langfuse (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 13591fd81486fc2001b5c998ff87badefcb81f4c396aa43675a7280a6fed23cf The package installs a Claude Code Stop hook and patches OpenCode plugin code so that every future AI session's user prompts, assistant responses, to...
MAL-2026-4532 Malicious code in code-tool-langfuse (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 13591fd81486fc2001b5c998ff87badefcb81f4c396aa43675a7280a6fed23cf The package installs a Claude Code Stop hook and patches OpenCode plugin code so that every future AI session's user prompts, assistant responses, to...
CVE-2026-5029
A remote code execution vulnerability exists in Code Runner MCP Server when run with the --transport http option, which exposes the /mcp JSON-RPC endpoint without authentication on port 3088. An unauthenticated remote attacker can invoke the run-code MCP tool to supply arbitrary source code and...
CVE-2026-5029 RCE in Code Runner MCP Server
A remote code execution vulnerability exists in Code Runner MCP Server when run with the --transport http option, which exposes the /mcp JSON-RPC endpoint without authentication on port 3088. An unauthenticated remote attacker can invoke the run-code MCP tool to supply arbitrary source code and...
Improper Access Control
@anthropic-ai/claude-code is vulnerable to improper access control. The vulnerability is due to an error in sed command parsing that bypasses read-only validation, which allows an attacker to write to arbitrary files on the host system...
CVE-2026-35020
Rejected reason: This CVE ID has been rejected by the its CVE Numbering Authority CNA. It was determined that the attack requires an attacker to already control arbitrary environment variables, a level of access they consider functionally equivalent to code execution and outside the threat model ...
CVE-2026-33068
Claude Code is an agentic coding tool. Versions prior to 2.1.53 resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set...
Arbitrary Code Injection
Overview @siteboon/claude-code-ui is an A web-based UI for Claude Code CLI Affected versions of this package are vulnerable to Arbitrary Code Injection in the git-config endpoint due to improper sanitization of user-supplied input in shell command construction. An attacker can execute arbitrary O...
Malicious code in alibabacloud-code-tool (PyPI)
--- -= Per source details. Do not edit below this line.=- Source: kam193 5e4d81a71d0710ac3618ec41e8027ee6a96ae9845ca67b33b950c8d99d8d2e8a This package impersonates Alibaba Cloud account and contains highly obfuscated code. --- Category: MALICIOUS - The campaign has clearly malicious intent, like...
MAL-2026-915 Malicious code in alibabacloud-code-tool (PyPI)
--- -= Per source details. Do not edit below this line.=- Source: kam193 5e4d81a71d0710ac3618ec41e8027ee6a96ae9845ca67b33b950c8d99d8d2e8a This package impersonates Alibaba Cloud account and contains highly obfuscated code. --- Category: MALICIOUS - The campaign has clearly malicious intent, like...
CVE-2025-64755
Claude Code is an agentic coding tool. Prior to version 2.0.31, due to an error in sed command parsing, it was possible to bypass the Claude Code read-only validation and write to arbitrary files on the host system. This issue has been patched in version 2.0.31...
The vulnerability of the Claude Code tool, related to improper cleaning of input data, allows a perpetrator to execute arbitrary commands.
The vulnerability of the Claude Code tool arises due to incorrect cleaning of input data. Exploiting this vulnerability allows a remote attacker to compromise confidentiality and execute arbitrary commands...