TitanCA: Lessons from Orchestrating LLM Agents to Discover 100+ CVEs

Software vulnerabilities remain one of the most persistent threats to modern digital infrastructure. While static application security testing SAST tools have long served as the first line of defense, they suffer from high false-positive rates. This article presents TitanCA, a collaborative proje...

CVE-2026-40217

A flaw was found in LiteLLM. A remote attacker can exploit this flaw by performing bytecode rewriting at the /guardrails/testcustomcode URI. This could lead to arbitrary code execution, allowing the attacker to run malicious code on the affected system. Mitigation Mitigation for this issue is...

Aether Smart Contract Security Analysis Framework 5.0.2

Aether is a Python-based framework for analyzing Solidity smart contracts, generating vulnerability findings, producing Foundry-based proof-of-concept PoC tests, and validating exploits on mainnet forks. It combines Solidity AST parsing, taint analysis, control flow graph analysis, cross-contract...

EUVD-2026-19637

A path traversal vulnerability exists in mintplex-labs/anything-llm versions up to and including 1.9.1, within the AgentFlows component. The vulnerability arises from improper handling of user input in the loadFlow and deleteFlow methods in server/utils/agentFlows/index.js. Specifically, the...

CVE-2026-5627

A path traversal vulnerability exists in mintplex-labs/anything-llm versions up to and including 1.9.1, within the AgentFlows component. The vulnerability arises from improper handling of user input in the loadFlow and deleteFlow methods in server/utils/agentFlows/index.js. Specifically, the...

CVE-2026-5627

The CVE-2026-5627 issue affects mintplex-labs/anything-llm up to version 1.9.1, specifically in the AgentFlows component. The vulnerability stems from improper handling of user input in loadFlow and deleteFlow (server/utils/agentFlows/index.js), where path.join combined with normalizePath can byp...

CVE-2026-5627 Path Traversal in mintplex-labs/anything-llm

A path traversal vulnerability exists in mintplex-labs/anything-llm versions up to and including 1.9.1, within the AgentFlows component. The vulnerability arises from improper handling of user input in the loadFlow and deleteFlow methods in server/utils/agentFlows/index.js. Specifically, the...

PT-2026-30828

A path traversal vulnerability exists in mintplex-labs/anything-llm versions up to and including 1.9.1, within the AgentFlows component. The vulnerability arises from improper handling of user input in the loadFlow and deleteFlow methods in server/utils/agentFlows/index.js. Specifically, the...

CritBench: A Framework for Evaluating Cybersecurity Capabilities of Large Language Models in IEC 61850 Digital Substation Environments

The advancement of Large Language Models LLMs has raised concerns regarding their dual-use potential in cybersecurity. Existing evaluation frameworks overwhelmingly focus on Information Technology IT environments, failing to capture the constraints, and specialized protocols of Operational...

anything-llm 安全漏洞

anything-llm is an integrated desktop and Docker AI application developed by Mintplex. Versions of anything-llm prior to 1.9.1 contain security vulnerabilities. These vulnerabilities stem from the improper handling of user input by the AgentFlows component, which may lead to path traversal attack...

CVE-2026-35030

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.83.0, when JWT authentication is enabled enablejwtauth: true, the OIDC userinfo cache uses token:20 as the cache key. JWT headers produced by the same signing algorithm generate identical first 20...

CVE-2026-35030 LiteLLM has an authentication bypass via OIDC userinfo cache key collision

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.83.0, when JWT authentication is enabled enablejwtauth: true, the OIDC userinfo cache uses token:20 as the cache key. JWT headers produced by the same signing algorithm generate identical first 20...

LiteLLM 安全漏洞

LiteLLM is an open-source application developed by Berri AI. It allows for the invocation of all LLM APIs in the OpenAI format. Versions of LiteLLM prior to 1.83.0 contained a security vulnerability. This vulnerability stemmed from the lack of enforceable administrator role authorization for the...

vLLM 安全漏洞

vLLM is an open-source solution designed for LLM-based models, featuring high throughput and memory-efficient reasoning and service engines. Versions of vLLM prior to 0.7.0 to 0.19.0 contained security vulnerabilities. These vulnerabilities stemmed from the VideoMediaIO.loadbase64 method not...

LiteLLM: Authentication bypass via OIDC userinfo cache key collision

Impact When JWT authentication is enabled enablejwtauth: true, the OIDC userinfo cache uses token:20 as the cache key. JWT headers produced by the same signing algorithm generate identical first 20 characters. This configuration option is not enabled by default. Most instances are not affected. A...

Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study

Third-party skills extend LLM agents with powerful capabilities but often handle sensitive credentials in privileged environments, making leakage risks poorly understood. We present the first large-scale empirical study of this problem, analyzing 17,022 skills sampled from 170,226 on SkillsMP usi...

CVE-2026-34760 vLLM: Downmix Implementation Differences as Attack Vectors Against Audio AI Models

vLLM is an inference and serving engine for large language models LLMs. From version 0.5.5 to before version 0.18.0, Librosa defaults to using numpy.mean for mono downmixing tomono, while the international standard ITU-R BS.775-4 specifies a weighted downmixing algorithm. This discrepancy results...

EUVD-2026-17146

A vulnerability was detected in raine consult-llm-mcp up to 2.5.3. Affected by this vulnerability is the function childprocess.execSync of the file src/server.ts. The manipulation of the argument gitdiff.baseref/gitdiff.files results in os command injection. The attack is only possible with local...

CVE-2026-29872

A cross-session information disclosure vulnerability exists in the awesome-llm-apps project in commit e46690f99c3f08be80a9877fab52acacf7ab8251 2026-01-19. The affected Streamlit-based GitHub MCP Agent stores user-supplied API tokens in process-wide environment variables using os.environ without...

CVE-2026-5125

A vulnerability was detected in raine consult-llm-mcp up to 2.5.3. Affected by this vulnerability is the function childprocess.execSync of the file src/server.ts. The manipulation of the argument gitdiff.baseref/gitdiff.files results in os command injection. The attack is only possible with local...