CVE-2026-25879 Langroid has Prompt to SQL Injection, Leading to RCE

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.63.0, SQLChatAgent executes SQL produced by an LLM, which is influenceable by prompt injection. When configured with a database role that has privileges enabling code execution or filesystem access...

EUVD-2026-33750

CodexBar prior to 0.32.0 contains a privilege escalation vulnerability in the CLI installer that allows local attackers to execute arbitrary commands as root by exploiting a race condition in temporary file handling. The installer creates a temporary file with mktemp, writes a privileged shell...

-cascade-scan

cascade-scan AI Agent security evaluation framework — autom...

CVE-2026-10210

A vulnerability was found in AstrBotDevs AstrBot 4.23.6. Affected by this vulnerability is the function sanitizepromptdescription of the file astrbot/core/skills/skillmanager.py. The manipulation results in injection. The attack may be performed from remote. The exploit has been made public and...

CVE-2026-10210 AstrBotDevs AstrBot skill_manager.py _sanitize_prompt_description injection

A vulnerability was found in AstrBotDevs AstrBot 4.23.6. Affected by this vulnerability is the function sanitizepromptdescription of the file astrbot/core/skills/skillmanager.py. The manipulation results in injection. The attack may be performed from remote. The exploit has been made public and...

CVE-2026-10210

The CVE affects AstrBotDevs AstrBot 4.23.6. The vulnerable component is the function _sanitize_prompt_description in astrbot/core/skills/skill_manager.py, where input handling allows injection due to improper sanitization. This vulnerability is reachable over a network (remote exploit) and, per t...

CVE-2026-10210 AstrBotDevs AstrBot skill_manager.py _sanitize_prompt_description injection

A vulnerability was found in AstrBotDevs AstrBot 4.23.6. Affected by this vulnerability is the function sanitizepromptdescription of the file astrbot/core/skills/skillmanager.py. The manipulation results in injection. The attack may be performed from remote. The exploit has been made public and...

CVE-2026-10210

A vulnerability was found in AstrBotDevs AstrBot 4.23.6. Affected by this vulnerability is the function sanitizepromptdescription of the file astrbot/core/skills/skillmanager.py. The manipulation results in injection. The attack may be performed from remote. The exploit has been made public and...

EUVD-2026-33531

A vulnerability was found in AstrBotDevs AstrBot 4.23.6. Affected by this vulnerability is the function sanitizepromptdescription of the file astrbot/core/skills/skillmanager.py. The manipulation results in injection. The attack may be performed from remote. The exploit has been made public and...

PT-2026-45242

A vulnerability was found in AstrBotDevs AstrBot 4.23.6. Affected by this vulnerability is the function sanitize prompt description of the file astrbot/core/skills/skill manager.py. The manipulation results in injection. The attack may be performed from remote. The exploit has been made public an...

Langroid 代码注入漏洞

Langroid is an open-source tool developed using multi-agent programming for LLM tasks. Versions of Langroid prior to 0.63.0 contained a code injection vulnerability. This vulnerability stemmed from SQLChatAgent executing SQL statements generated by the LLM. It could be exploited via prompt...

AstrBot 安全漏洞

AstrBot is an open-source multi-platform LLM chatbot and development framework created by AstrBot. Version 4.23.6 of AstrBot contains a security vulnerability, which stems from an injection vulnerability in the sanitizepromptdescription function located in the astrbot/core/skills/skillmanager.py...

PT-2026-45557

Name of the Vulnerable Software and Affected Versions CodexBar versions prior to 0.32.0 Description A privilege escalation issue exists in the CLI installer. Local attackers can execute arbitrary commands as root by exploiting a race condition—a situation where the system's behavior depends on th...

AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations

Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations third-party services such as Gmail, Salesforce, or Jira accessed through tool calls whose response content the user neither writes nor controls. Existing benchmarks under-measure the...

Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety

Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not scale, LLM-as-attacker methods exhibit mode collapse, and gradient-based approaches produce uninterpretable gibberish. We introduce a quality-diversity evolutionary framework that operates at the...

Exposure of Sensitive System Information to an Unauthorized Control Sphere

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context

Summary PraisonAI's direct-prompt CLI automatically expands @url: mentions in raw prompt text before agent execution begins. If a prompt contains @url:, the CLI calls MentionsParser.process.... The @url: handler then performs a direct urllib.request.urlopen request to the attacker-controlled URL...

GHSA-5CXW-77WG-JRF3 PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context

Summary PraisonAI's direct-prompt CLI automatically expands @url: mentions in raw prompt text before agent execution begins. If a prompt contains @url:, the CLI calls MentionsParser.process.... The @url: handler then performs a direct urllib.request.urlopen request to the attacker-controlled URL...

Exposure of Sensitive System Information to an Unauthorized Control Sphere

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Exposure of Sensitive System Information to an Unauthorized Control Sphere via the direct-prompt CLI. An attacker can access sensitive local...

ChatGPhish Vulnerability Turns ChatGPT Web Summaries Into a Phishing Surface

Cybersecurity researchers have disclosed details of a vulnerability in OpenAI ChatGPT that leverages the artificial intelligence AI assistant's implicit trust in Markdown links and images to trigger prompt injections and open the door to phishing attacks. The technique has been codenamed ChatGPhi...