AARTF---Autonomous-AI-RedTeam-Framework

AARTF AI-Driven Autonomous Security Workflow !CIhttps:/...

CVE-2026-5323

The CVE-2026-5323 entry affects priyankark a11y-mcp (up to 1.0.5), specifically the A11yServer function in src/index.js, causing a server-side request forgery. Exploitation requires a local position. An exploit has been made public. Upgrade to version 1.0.6 to resolve, with patch id e3e11c9e8482b...

PT-2026-29938

act: Unrestricted set-env and add-path command processing enables environment injection in github.com/nektos/act...

AgentWatcher: A Rule-Based Prompt Injection Monitor

Large language models LLMs and their applications, such as agents, are highly vulnerable to prompt injection attacks. State-of-the-art prompt injection detection methods have the following limitations: 1 their effectiveness degrades significantly as context length increases, and 2 they lack...

mcp-handler has a tool response leak across concurrent client sessions ('Race Condition')

mcp-handler versions prior to 1.1.0 accepted @modelcontextprotocol/sdk =1.26.0, which contains the fix for CVE-2026-25536. Workarounds - Upgrade @modelcontextprotocol/sdk to =1.26.0 note: the SDK will throw on transport reuse, which will break mcp-handler 1.1.0 which effectively forces the upgrad...

PraisonAI Has Authentication Bypass via OAuthManager.validate_token()

Summary OAuthManager.validatetoken returns True for any token not found in its internal store, which is empty by default. Any HTTP request to the MCP server with an arbitrary Bearer token is treated as authenticated, granting full access to all registered tools and agent capabilities. Details...

PraisonAI Has ReDoS via Unvalidated User-Controlled Regex in MCPToolIndex.search_tools()

Summary MCPToolIndex.searchtools compiles a caller-supplied string directly as a Python regular expression with no validation, sanitization, or timeout. A crafted regex causes catastrophic backtracking in the re engine, blocking the Python thread for hundreds of seconds and causing a complete...

GHSA-8W9J-HC3G-3G7F PraisonAI Has ReDoS via Unvalidated User-Controlled Regex in MCPToolIndex.search_tools()

Summary MCPToolIndex.searchtools compiles a caller-supplied string directly as a Python regular expression with no validation, sanitization, or timeout. A crafted regex causes catastrophic backtracking in the re engine, blocking the Python thread for hundreds of seconds and causing a complete...

CVE-2026-34451

Claude SDK for TypeScript provides access to the Claude API from server-side TypeScript or JavaScript applications. From version 0.79.0 to before version 0.81.0, the local filesystem memory tool in the Anthropic TypeScript SDK validated model-supplied paths using a string prefix check that did no...

CVE-2026-34548

iccDEV provides a set of libraries and tools for working with ICC color management profiles. Prior to version 2.3.1.6, there is an Undefined Behavior UB condition in the XML conversion tooling path iccToXml caused by an implicit conversion from a negative signed integer to icUInt32Number unsigned...

CVE-2026-34450

The Claude SDK for Python provides access to the Claude API from Python applications. From version 0.86.0 to before version 0.87.0, the local filesystem memory tool in the Anthropic Python SDK created memory files with mode 0o666, leaving them world-readable on systems with a standard umask and...

CVE-2026-34452

The Claude SDK for Python provides access to the Claude API from Python applications. From version 0.86.0 to before version 0.87.0, the async local filesystem memory tool in the Anthropic Python SDK validated that model-supplied paths resolved inside the sandboxed memory directory, but then...

EUVD-2026-17681

Claude SDK for Python: Memory Tool Path Validation Race Condition Allows Sandbox Escape...

Claude SDK for Python: Memory Tool Path Validation Race Condition Allows Sandbox Escape

The async local filesystem memory tool in the Anthropic Python SDK validated that model-supplied paths resolved inside the sandboxed memory directory, but then returned the unresolved path for subsequent file operations. A local attacker able to write to the memory directory could retarget a...

GHSA-W828-4QHX-VXX3 Claude SDK for Python: Memory Tool Path Validation Race Condition Allows Sandbox Escape

The async local filesystem memory tool in the Anthropic Python SDK validated that model-supplied paths resolved inside the sandboxed memory directory, but then returned the unresolved path for subsequent file operations. A local attacker able to write to the memory directory could retarget a...

Directory Traversal

Overview @anthropic-ai/sdk is a The official TypeScript library for the Anthropic API Affected versions of this package are vulnerable to Directory Traversal via improper validation of user-supplied paths in the memory tool. An attacker can access or modify files outside the intended sandboxed...

EUVD-2026-17679

Claude SDK for TypeScript: Memory Tool Path Validation Allows Sandbox Escape to Sibling Directories...

Claude SDK for TypeScript: Memory Tool Path Validation Allows Sandbox Escape to Sibling Directories

The local filesystem memory tool in the Anthropic TypeScript SDK validated model-supplied paths using a string prefix check that did not append a trailing path separator. A model steered by prompt injection could supply a crafted path that resolved to a sibling directory sharing the memory root's...

Incorrect Permission Assignment for Critical Resource

Overview anthropic is a The official Python library for the anthropic API Affected versions of this package are vulnerable to Incorrect Permission Assignment for Critical Resource in the local filesystem memory tool due to files being created with overly permissive permissions. An attacker can...

Claude SDK for Python has Insecure Default File Permissions in Local Filesystem Memory Tool

The local filesystem memory tool in the Anthropic Python SDK created memory files with mode 0o666, leaving them world-readable on systems with a standard umask and world-writable in environments with a permissive umask such as many Docker base images. A local attacker on a shared host could read...