SoK: The Attack Surface of Agentic AI -- Tools, and Autonomy

Recent AI systems combine large language models with tools, external knowledge via retrieval-augmented generation RAG, and even autonomous multi-agent decision loops. This agentic AI paradigm greatly expands capabilities - but also vastly enlarges the attack surface. In this systematization, we m...

We Found Eight Attack Vectors Inside AWS Bedrock. Here's What Attackers Can Do with Them

AWS Bedrock is Amazon's platform for building AI-powered applications. It gives developers access to foundation models and the tools to connect those models directly to enterprise data and systems. That connectivity is what makes it powerful – but it’s also what makes Bedrock a target. When an AI...

EUVD-2026-14385

An unauthenticated remote attacker can exploit a hidden function in the CLI prompt to escape the restricted interface and gain root access to the underlying Linux based OS, leading to full compromise of the device...

CVE-2026-3587

An unauthenticated remote attacker can exploit a hidden function in the CLI prompt to escape the restricted interface, leading to full compromise of the device...

CVE-2026-3587 Hidden CLI Function Allows Root Access

An unauthenticated remote attacker can exploit a hidden function in the CLI prompt to escape the restricted interface, leading to full compromise of the device...

WAGO Lean Managed Switch 安全漏洞

WAGO Lean Managed Switch is a software developed by the German company WAGO, used for managing and monitoring WAGO Lean series switches. There is a security vulnerability in the WAGO Lean Managed Switch, which stems from hidden functions in the CLI prompt. This vulnerability could potentially lea...

PT-2026-27066

Name of the Vulnerable Software and Affected Versions WAGO Lean Managed Switch 852-1812 and other WAGO products versions prior to a fix for CVE-2026-3587 Description An unauthenticated remote attacker can exploit a hidden function within the Command Line Interface CLI prompt to bypass the...

GHSA-8MR2-F9WF-HCFQ Duplicate Advisory: OpenClaw reuses the gateway auth token in the owner ID prompt hashing fallback

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-v6x2-2qvm-6gv8. This link is maintained to preserve external references. Original Description OpenClaw versions prior to 2026.2.22 reuse gateway.auth.token as a fallback hash secret for owner-ID prompt obfuscati...

EUVD-2026-13974

OpenClaw versions prior to 2026.2.22 reuse gateway.auth.token as a fallback hash secret for owner-ID prompt obfuscation when commands.ownerDisplay is set to hash and commands.ownerDisplaySecret is unset, creating dual-use of authentication secrets across security domains. Attackers with access to...

CVE-2026-32897

OpenClaw versions prior to 2026.2.22 reuse gateway.auth.token as a fallback hash secret for owner-ID prompt obfuscation when commands.ownerDisplay is set to hash and commands.ownerDisplaySecret is unset, creating dual-use of authentication secrets across security domains. Attackers with access to...

CVE-2026-32897 OpenClaw < 2026.2.22 - Authentication Token Reuse in Owner ID Prompt Hashing Fallback

OpenClaw versions prior to 2026.2.22 reuse gateway.auth.token as a fallback hash secret for owner-ID prompt obfuscation when commands.ownerDisplay is set to hash and commands.ownerDisplaySecret is unset, creating dual-use of authentication secrets across security domains. Attackers with access to...

CVE-2026-32897 OpenClaw < 2026.2.22 - Authentication Token Reuse in Owner ID Prompt Hashing Fallback

OpenClaw versions prior to 2026.2.22 reuse gateway.auth.token as a fallback hash secret for owner-ID prompt obfuscation when commands.ownerDisplay is set to hash and commands.ownerDisplaySecret is unset, creating dual-use of authentication secrets across security domains. Attackers with access to...

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...

CVE-2026-33060

CKAN MCP Server is a tool for querying CKAN open data portals. Versions prior to 0.4.85 provide tools including ckanpackagesearch and sparqlquery that accept a baseurl parameter, making HTTP requests to arbitrary endpoints without restriction. A CKAN portal client has no legitimate reason to...

CVE-2026-33060: Server-Side Request Forgery (SSRF)

CKAN MCP Server is a tool for querying CKAN open data portals. Versions prior to 0.4.85 provide tools including ckanpackagesearch and sparqlquery that accept a baseurl parameter, making HTTP requests to arbitrary endpoints without restriction. A CKAN portal client has no legitimate reason to...

EUVD-2026-13294

OpenClaw versions prior to 2026.2.24 contain an approval gating bypass vulnerability in system.run allowlist mode where nested transparent dispatch wrappers can suppress shell-wrapper detection. Attackers can exploit this by chaining multiple dispatch wrappers like /usr/bin/env to execute /bin/sh...

CVE-2026-32622

SQLBot is an intelligent data query system based on a large language model and RAG. Versions 1.5.0 and below contain a Stored Prompt Injection vulnerability that chains three flaws: a missing permission check on the Excel upload API allowing any authenticated user to upload malicious terminology,...

CVE-2026-27740

Discourse is an open-source discussion platform. Versions prior to 2026.3.0-latest.1, 2026.2.1, and 2026.1.2 have a cross-site scripting vulnerability that arises because the system trusts the raw output from an AI Large Language Model LLM and renders it using htmlSafe in the Review Queue interfa...

CVE-2026-27740

Discourse (open-source discussion platform) is affected by CVE-2026-27740. Versions prior to 2026.3.0-latest.1, 2026.2.1, and 2026.1.2 are vulnerable to stored XSS caused by trusting raw output from an AI Large Language Model and rendering it with htmlSafe in the Review Queue without adequate san...

CVE-2026-32622

SQLBot (versions ≤ 1.5.x) exposes a Stored Prompt Injection vulnerability consisting of three chained flaws: (1) missing permission check on the Excel upload API allowing any authenticated user to upload malicious terminology, (2) unsanitized storage of terminology descriptions containing dangero...