CVE-2026-8321

A vulnerability was detected in inkeep agents 0.58.14. This vulnerability affects the function createDevContext of the file agents-api/src/middleware/runAuth.ts of the component runAuth Middleware. Performing a manipulation results in authentication bypass using alternate channel. The attack is...

CVE-2026-8319 aiwaves-cn agents cheshire_cat_core stray_cat.py recall_relevant_memories_to_working_memory resource consumption

A weakness has been identified in aiwaves-cn agents up to e8c4e3c2d19739d3dff59e577d1c97090cc15f59. Affected by this issue is the function recallrelevantmemoriestoworkingmemory of the file core/cat/lookingglass/straycat.py of the component cheshirecatcore. This manipulation causes resource...

CVE-2026-8319 aiwaves-cn agents cheshire_cat_core stray_cat.py recall_relevant_memories_to_working_memory resource consumption

A weakness has been identified in aiwaves-cn agents up to e8c4e3c2d19739d3dff59e577d1c97090cc15f59. Affected by this issue is the function recallrelevantmemoriestoworkingmemory of the file core/cat/lookingglass/straycat.py of the component cheshirecatcore. This manipulation causes resource...

EUVD-2026-29143

OpenClaw before 2026.4.20 contains a tool policy bypass vulnerability allowing bundled MCP and LSP tools to circumvent configured tool restrictions. Attackers with local agent access can append restricted tools to the effective tool set after policy filtering, bypassing profile policies, allow/de...

databricks-agents (>=0.1.0 <=1.0.0rc1), datamint (>=2.5.0 <=2.5.2) +3 more potentially affected by CVE-2026-2393 via mlflow (>=3.0.0rc2 <=3.0.1)

mlflow PYPI version =3.0.0rc2, =0.1.0, =2.5.0, =0.2.0.dev0, =0.6.7, =0.8.1 Source cves: CVE-2026-2393 Source advisory: SNYK:PYTHON-MLFLOW-16642071...

azure-ai-generative (>=1.0.0b1 <=1.0.0b3), azure-ai-resources (>=1.0.0b1 <=1.0.0b9) +15 more potentially affected by CVE-2026-2393 via mlflow-skinny (>=3.0.0 <=3.0.1)

mlflow-skinny PYPI version =3.0.0, =1.0.0b1, =1.0.0b1, =0.1.0, =0.1.0, =2.5.0, =0.0.13, =3.0.0, =0.1.0, =0.1.4 and more Source cves: CVE-2026-2393 Source advisory: SNYK:PYTHON-MLFLOWSKINNY-16642072...

CVE-2026-44997

OpenClaw before 2026.4.22 contains a security envelope constraint bypass vulnerability allowing restricted subagents to spawn ACP child sessions that fail to inherit depth, child-count limits, control scope, or target-agent restrictions. Attackers can exploit this by spawning child sessions that...

PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables execute

Summary praisonaiagents resolves unresolved tool names against module globals and main after it fails to match the declared tool list and the registry. With the default agent configuration, permallow is None, so undeclared non-dangerous tool names are not rejected by the permission gate. An...

PraisonAI ships and generates a legacy API server with authentication disabled by default, allowing unauthenticated workflow execution

Summary PraisonAI ships a legacy Flask API server with authentication disabled by default. When that server is used, any caller that can reach it can access /agents and trigger the configured agents.yaml workflow through /chat without providing a token. Details The vulnerable server is the shippe...

GHSA-6RMH-7XCM-CPXJ PraisonAI ships and generates a legacy API server with authentication disabled by default, allowing unauthenticated workflow execution

Summary PraisonAI ships a legacy Flask API server with authentication disabled by default. When that server is used, any caller that can reach it can access /agents and trigger the configured agents.yaml workflow through /chat without providing a token. Details The vulnerable server is the shippe...

Can a Single Message Paralyze the AI Infrastructure? the Rise of AbO-DDoS Attacks through Targeted Mobius Injection

Large Language Model LLM agents have emerged as key intermediaries, orchestrating complex interactions between human users and a wide range of digital services and LLM infrastructures. While prior research has extensively examined the security of LLMs and agents in isolation, the systemic risk of...

agents 资源管理错误漏洞

Agents is an open-source intelligent agent symbol learning and training framework developed by AIWaves. There is a resource management vulnerability in aiwaves-cn agents, which stems from the recallrelevantmemoriestoworkingmemory function in the core/cat/lookingglass/straycat.py file within the...

PT-2026-39741

Name of the Vulnerable Software and Affected Versions aiwaves-cn agents up to e8c4e3c2d19739d3dff59e577d1c97090cc15f59 Description A flaw in the cheshire cat core component, specifically within the recall relevant memories to working memory function located in the core/cat/looking glass/stray...

PT-2026-39756

A vulnerability was detected in inkeep agents 0.58.14. This vulnerability affects the function createDevContext of the file agents-api/src/middleware/runAuth.ts of the component runAuth Middleware. Performing a manipulation results in authentication bypass using alternate channel. The attack is...

Inkeep Agents 授权问题漏洞

Inkeep Agents is an open-source tool developed by Inkeep, designed for building AI agents that support visual drag-and-drop operations and TypeScript SDKs. Version 0.58.14 of Inkeep Agents contains a vulnerability related to authorization. This vulnerability originates from the createDevContext...

kernel-exploit-intelligence

🐧 Kernel Exploit Intelligence KEI !KEI Logo./assets/logo...

Dark-Moon

The Open-Source AI-...

Trust Me, Import This: Dependency Steering Attacks Via Malicious Agent Skills

LLM-powered coding agents increasingly make software supply chain decisions. They generate imports, recommend packages, and write installation commands. Prior work showed that these systems can hallucinate non-existent package names, which attackers may register as malicious packages. In this...

Security Risks in Tool-Enabled AI Agents: A Systematic Analysis of Privileged Execution Environments

Tool-enabled AI agents are increasingly deployed in cloud-hosted environments and offered as services, where they perform side-effecting operations through privileged tools within execution environments. While such agents enable powerful automation, the security implications of hosting autonomous...

AgentShield: Deception-Based Compromise Detection for Tool-Using LLM Agents

Defenses against indirect prompt injection IPI in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks rather than detect the compromises that slip through. Second, they have only been evaluated in English, leaving users of low-resource languages such ...