PrivateGPT < 0.5.0 - Open Redirect

An open redirect vulnerability exists in imartinez/privategpt version 0.5.0 due to improper handling of the 'file' parameter. This vulnerability allows attackers to redirect users to a URL specified by user-controlled input without proper validation or sanitization. id: CVE-2024-5936 info: name:...

GPT Academic v1.3.9 - Open Redirect

An open redirect vulnerability exists in GPT Academic v1.3.9, where the file parameter in the /file= endpoint can be manipulated to redirect users to malicious websites. This could facilitate phishing attacks by tricking users into visiting attacker-controlled URLs. id: CVE-2024-10812 info: name:...

CVE-2026-10566 FoundationAgents MetaGPT schema.py Message.check_instruct_content deserialization

A weakness has been identified in FoundationAgents MetaGPT up to 0.8.2. This affects the function Message.checkinstructcontent of the file metagpt/schema.py. Executing a manipulation of the argument mapping can lead to deserialization. The attack is restricted to local execution. The exploit has...

EUVD-2026-33872

A weakness has been identified in FoundationAgents MetaGPT up to 0.8.2. This affects the function Message.checkinstructcontent of the file metagpt/schema.py. Executing a manipulation of the argument mapping can lead to deserialization. The attack is restricted to local execution. The exploit has...

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...

CVE-2026-33232

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Versions 0.4.2 through 0.6.51 are vulnerable to an unauthenticated Denial of Service DoS through the server due to uncontrolled disk space consumption. The downloadagentfile...

CVE-2026-33234 AutoGPT: SendEmailBlock's IP blocklist bypass allows SSRF via user-controlled SMTP server

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions 0.1.0 through 0.6.51, SendEmailBlock in autogptplatform/backend/backend/blocks/emailblock.py accepts a user-supplied smtpserver string and smtpport integer as...

CVE-2026-33233

CVE-2026-33233 affects AutoGPT Platform: older releases (0.6.34–0.6.51) deserialize Redis cache bytes with pickle.loads without integrity checks, while writes use pickle.dumps into Redis. The read path blindly calls pickle.loads on bytes with no HMAC/signature or strict schema validation. An atta...

CVE-2026-33232

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Versions 0.4.2 through 0.6.51 are vulnerable to an unauthenticated Denial of Service DoS through the server due to uncontrolled disk space consumption. The downloadagentfile...

EUVD-2026-30819

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Versions 0.4.2 through 0.6.51 are vulnerable to an unauthenticated Denial of Service DoS through the server due to uncontrolled disk space consumption. The downloadagentfile...

@jsr2npm/yao__gpt-vis-mcp (>=0.0.1 <=0.1.1), @ly_agent/ly-vis-mcp-server (=0.1.14) +3 more potentially affected by unknown CVE via @antv/gpt-vis-ssr (>=0.1.10 <=0.3.7)

@antv/gpt-vis-ssr NPM version =0.1.10, =0.0.1, =0.0.1, =1.0.0, =1.0.0, =1.0.2 Source cves: unknown CVE Source advisory: OSV:MAL-2026-4021...

Malicious code in @antv/gpt-vis-ssr (npm)

Part of the Mini Shai-Hulud supply chain attack campaign in which a threat actor compromised the npm account atool and published 631 malicious versions across 314 npm packages in an automated 22-minute burst. Each malicious version injects a preinstall hook that executes a 498KB obfuscated Bun...

@antv/gpt-vis-ssr (>=0.3.4 <=0.3.7), @tiangong-ai/vis-server (>=0.0.1 <=0.0.5) potentially affected by unknown CVE via @antv/s2-ssr (>=0.0.2 <=0.1.1)

@antv/s2-ssr NPM version =0.0.2, =0.3.4, =0.0.1, =0.0.5 Source cves: unknown CVE Source advisory: OSV:MAL-2026-4080...

@antv/gpt-vis (=0.5.0-beta.0), @antv/gpt-vis-ssr (>=0.1.0 <=0.3.7) +7 more potentially affected by unknown CVE via @antv/g2-ssr (>=0.0.8 <=0.2.0)

@antv/g2-ssr NPM version =0.0.8, =0.1.0, =0.0.1, =0.0.1, =1.0.0, =1.0.0, =1.0.2 Source cves: unknown CVE Source advisory: OSV:MAL-2026-3979...

MAL-2026-4020 Malicious code in @antv/gpt-vis (npm)

Part of the Mini Shai-Hulud supply chain attack campaign in which a threat actor compromised the npm account atool and published 631 malicious versions across 314 npm packages in an automated 22-minute burst. Each malicious version injects a preinstall hook that executes a 498KB obfuscated Bun...

@antv/ava (=3.6.0-alpha.0), @antv/g (>=6.0.0 <=6.2.1) +6 more potentially affected by unknown CVE via @antv/g-camera-api (>=2.0.0 <=2.0.9)

@antv/g-camera-api NPM version =2.0.0, =6.0.0, =0.5.9, =2.0.0, =1.2.5, =1.2.6 - expression-language-editor =0.0.4 Source cves: unknown CVE Source advisory: OSV:MAL-2026-3910...

@antv/gpt-vis (=0.5.0-beta.0), @antv/gpt-vis-ssr (>=0.1.0 <=0.3.7) +6 more potentially affected by unknown CVE via @antv/g6-ssr (>=0.0.16 <=0.1.1)

@antv/g6-ssr NPM version =0.0.16, =0.1.0, =0.0.1, =0.0.1, =0.2.1, =1.0.0, =1.0.0, =1.0.2 Source cves: unknown CVE Source advisory: OSV:MAL-2026-3996...

@antv/gpt-vis (>=1.0.0 <=1.0.0-beta.2) potentially affected by unknown CVE via @antv/t8 (=0.3.0)

@antv/t8 NPM version =0.3.0 is affected by a known vulnerability. The following packages have a transitive dependency on @antv/t8 and may be impacted: - @antv/gpt-vis =1.0.0, =1.0.0-beta.2 Source cves: unknown CVE Source advisory: OSV:MAL-2026-4087...

MAL-2026-4021 Malicious code in @antv/gpt-vis-ssr (npm)

Part of the Mini Shai-Hulud supply chain attack campaign in which a threat actor compromised the npm account atool and published 631 malicious versions across 314 npm packages in an automated 22-minute burst. Each malicious version injects a preinstall hook that executes a 498KB obfuscated Bun...

CVE-2025-32425

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. In AutoGPT, the execution process is recorded to the console stdout/stderr, and deployed in container mode, which is automatically captured by Docker an...