CVE-2026-42079 PPTAgent: Arbitrary Code Execution via Python eval() of LLM-Generated Code with Builtins in Scope

PPTAgent is an agentic framework for reflective PowerPoint generation. Prior to commit 418491a, PPTAgent is vulnerable to arbitrary code execution via Python eval of LLM-generated code with builtins in scope. This issue has been patched via commit 418491a...

CVE-2026-42079 PPTAgent: Arbitrary Code Execution via Python eval() of LLM-Generated Code with Builtins in Scope

PPTAgent is an agentic framework for reflective PowerPoint generation. Prior to commit 418491a, PPTAgent is vulnerable to arbitrary code execution via Python eval of LLM-generated code with builtins in scope. This issue has been patched via commit 418491a...

EUVD-2026-27009

Evolver is a GEP-powered self-evolving engine for AI agents. Prior to version 1.69.3, a command injection vulnerability in the extractLLM function allows attackers to execute arbitrary shell commands on the server. The function constructs a curl command using string concatenation and passes it to...

CVE-2026-42076

Evolver is a GEP-powered self-evolving engine for AI agents. Prior to version 1.69.3, a command injection vulnerability in the extractLLM function allows attackers to execute arbitrary shell commands on the server. The function constructs a curl command using string concatenation and passes it to...

CVE-2026-42076 Evolver: Command Injection via `execSync` in `_extractLLM()` function allows Remote Code Execution

Evolver is a GEP-powered self-evolving engine for AI agents. Prior to version 1.69.3, a command injection vulnerability in the extractLLM function allows attackers to execute arbitrary shell commands on the server. The function constructs a curl command using string concatenation and passes it to...

CVE-2026-42079: Improper Neutralization of Directives in Dynamically Evaluated Code

PPTAgent is an agentic framework for reflective PowerPoint generation. Prior to commit 418491a, PPTAgent is vulnerable to arbitrary code execution via Python eval of LLM-generated code with builtins in scope. This issue has been patched via commit 418491a...

ai.ancf.lmos-router:lmos-router-llm-in-spring-cloud-gateway-demo (>=0.2.0, <=0.28.0), ai.ancf.lmos:arc-graphql-spring-boot-starter (>=0.1.1, <=0.112.0) +1743 more potentially affected by CVE-2026-22741 via org.springframework:spring-webflux (>=6.1.0, <=6.1.21)

org.springframework:spring-webflux MAVEN version =6.1.0, =0.2.0, =0.1.1, =0.1.1, =0.0.4, =0.1.0, =0.6.0, =0.6.0, =0.5.0, =1.2.0, =1.1.0, =1.3.0 and more Source cves: CVE-2026-22741 Source advisory: OSV:GHSA-WG35-8JPF-2XV3...

ai.ancf.lmos-router:lmos-router-llm-in-spring-cloud-gateway-demo (>=0.2.0, <=0.28.0), ai.ancf.lmos:arc-graphql-spring-boot-starter (>=0.1.1, <=0.112.0) +1743 more potentially affected by CVE-2026-22740 via org.springframework:spring-webflux (>=6.1.0, <=6.1.21)

org.springframework:spring-webflux MAVEN version =6.1.0, =0.2.0, =0.1.1, =0.1.1, =0.0.4, =0.1.0, =0.6.0, =0.6.0, =0.5.0, =1.2.0, =1.1.0, =1.3.0 and more Source cves: CVE-2026-22740 Source advisory: GHSA-5843-P793-GHMM...

LiteLLM CVE-2026-42208 SQL Injection Exploited within 36 Hours of Disclosure

In yet another instance of threat actors quickly jumping on the exploitation bandwagon, a newly disclosed critical security flaw in BerriAI's LiteLLM Python package has come under active exploitation in the wild within 36 hours of the bug becoming public knowledge. The vulnerability, tracked as...

An Empirical Security Evaluation of LLM-Generated Cryptographic Rust Code

Developers and organizations are using Large Language Models LLMs to generate security-critical code more frequently than ever, including cryptographic solutions for their products. This study presents an empirical evaluation of cryptographic security in 240 Rust code samples for two crypto...

CVE-2026-7147

A vulnerability was detected in JoeCastrom mcp-chat-studio up to 1.5.0. Affected by this issue is some unknown functionality of the file server/routes/llm.js of the component LLM Models API. Performing a manipulation of the argument req.query.baseurl results in server-side request forgery. Remote...

CVE-2026-7147

JoeCastrom mcp-chat-studio (up to 1.5.0) contains a server-side request forgery (SSRF) vulnerability in the LLM Models API, specifically in file server/routes/llm.js. Manipulating the argument req.query.base_url can trigger SSRF, enabling remote exploitation. Public exploit appears available. The...

EUVD-2026-25906

A vulnerability was detected in JoeCastrom mcp-chat-studio up to 1.5.0. Affected by this issue is some unknown functionality of the file server/routes/llm.js of the component LLM Models API. Performing a manipulation of the argument req.query.baseurl results in server-side request forgery. Remote...

CVE-2026-7147 JoeCastrom mcp-chat-studio LLM Models API llm.js server-side request forgery

A vulnerability was detected in JoeCastrom mcp-chat-studio up to 1.5.0. Affected by this issue is some unknown functionality of the file server/routes/llm.js of the component LLM Models API. Performing a manipulation of the argument req.query.baseurl results in server-side request forgery. Remote...

CVE-2026-7147 JoeCastrom mcp-chat-studio LLM Models API llm.js server-side request forgery

A vulnerability was detected in JoeCastrom mcp-chat-studio up to 1.5.0. Affected by this issue is some unknown functionality of the file server/routes/llm.js of the component LLM Models API. Performing a manipulation of the argument req.query.baseurl results in server-side request forgery. Remote...

CVE-2026-7147: Server-Side Request Forgery (SSRF)

A vulnerability was detected in JoeCastrom mcp-chat-studio up to 1.5.0. Affected by this issue is some unknown functionality of the file server/routes/llm.js of the component LLM Models API. Performing a manipulation of the argument req.query.baseurl results in server-side request forgery. Remote...

Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents

Autonomous Large Language Model LLM agents are increasingly deployed to conduct complex tasks by interacting with external tools, APIs, and memory stores. However, processing untrusted external data exposes these agents to severe security threats, such as indirect prompt injection and unauthorize...

PT-2026-37185

Name of the Vulnerable Software and Affected Versions LiteLLM versions 1.74.2 through 1.83.6 Description LiteLLM, a proxy server for Large Language Model APIs, contains a flaw where two endpoints used to preview an MCP server before saving it accept a full server configuration in the request body...

document-qa-engine (>=0.5.1, <=0.6.0), kapso (>=0.1.0, <=0.1.5) +4 more potentially affected by CVE-2026-41488 via langchain-openai (0.3.18)

langchain-openai PYPI version 0.3.18 is affected by a known vulnerability. The following packages have a transitive dependency on langchain-openai and may be impacted: - document-qa-engine =0.5.1, =0.1.0, =0.1.1, =1.0.0, =1.0.1, =1.0.6 - veee 0.0.3 Source cves: CVE-2026-41488 Source advisory:...

bugbug (0.0.550), okazaki (>=0.0.2, <=0.0.4) +4 more potentially affected by CVE-2026-41488 via langchain-openai (0.1.17)

langchain-openai PYPI version 0.1.17 is affected by a known vulnerability. The following packages have a transitive dependency on langchain-openai and may be impacted: - bugbug 0.0.550 - okazaki =0.0.2, =0.1.1, =0.1.0, =0.3.3, =0.0.3, =0.7.0 Source cves: CVE-2026-41488 Source advisory:...