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: Remote Code Execution via Terminology Poisoning

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-2026-32622

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...

EUVD-2026-13210

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-2026-32622 SQLBot: Remote Code Execution via Terminology Poisoning

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-2026-32622 SQLBot: Remote Code Execution via Terminology Poisoning

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,...

PT-2026-26297

Name of the Vulnerable Software and Affected Versions Claude Code versions prior to 2.1.53 Description Claude Code is an agentic coding tool that experienced a loading order issue in its settings loader. The software resolved the permission mode from settings files, such as the...

PT-2026-26367

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,...

PT-2026-26361

Name of the Vulnerable Software and Affected Versions Discourse versions prior to 2026.3.0-latest.1 Discourse versions prior to 2026.2.1 Discourse versions prior to 2026.1.2 Description Discourse, an open-source discussion platform, is affected by a cross-site scripting issue. The system improper...

A Framework for Formalizing LLM Agent Security

Security in LLM agents is inherently contextual. For example, the same action taken by an agent may represent legitimate behavior or a security violation depending on whose instruction led to the action, what objective is being pursued, and whether the action serves that objective. However,...

SQLBot 安全漏洞

SQLBot is an intelligent data querying system developed by DataEase, based on large models and RAG techniques. Versions of SQLBot 1.5.0 and earlier contained security vulnerabilities. These vulnerabilities were caused by storage-based prompt injection attacks, which could allow attackers to hijac...

CVE-2026-32622: Missing Authorization

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: Improper Neutralization of Input During Web Page Generation

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...

Malicious code in chai-as-prompt (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 5b773fc994ff2fb27407b9ab4482deb4ab95bf5d772a226a80db73f0e0740b8b The package chai-as-prompt was found to contain malicious code...

MAL-2026-1669 Malicious code in chai-as-prompt (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 5b773fc994ff2fb27407b9ab4482deb4ab95bf5d772a226a80db73f0e0740b8b The package chai-as-prompt was found to contain malicious code...

PT-2026-96188

Name of the Vulnerable Software and Affected Versions @aborruso/ckan-mcp-server affected versions not specified Description Tools such as ckan package search, sparql query, and ckan datastore search sql accept a base url or server url parameter that allows making HTTP requests to arbitrary...

PISmith: Reinforcement Learning-Based Red Teaming for Prompt Injection Defenses

Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents. Although many defenses have been proposed, their robustness against adaptive attacks remains insufficiently evaluated, potentially creating a false sense of security. In this work, we...