What Is CAASM? Cyber Asset Attack Surface Management Explained

Your security team runs scans from five different tools. Each one gives you a different number of assets, a different count of vulnerabilities, and a different view of your risk. Meanwhile, your CMDB is outdated, shadow IT keeps expanding, and nobody can confidently answer a basic question: "What...

SIR-Bench: Evaluating Investigation Depth in Security Incident Response Agents

We present SIR-Bench, a benchmark of 794 test cases for evaluating autonomous security incident response agents that distinguishes genuine forensic investigation from alert parroting. Derived from 129 anonymized incident patterns with expert-validated ground truth, SIR-Bench measures not only...

The vulnerability of the software interface of the tool for creating and deploying agents and working processes in Langflow allows a perpetrator to execute arbitrary code.

The vulnerability of the software interface of the tool for creating and deploying agents and processes of Langflow is related to the absence of authentication for a critical function. Exploiting this vulnerability allows a remote attacker to execute arbitrary code...

EUVD-2026-21696

A vulnerability was identified in FoundationAgents MetaGPT up to 0.8.1. This affects the function generatethoughts of the file metagpt/strategy/tot.py of the component Tree-of-Thought Solver. The manipulation leads to code injection. It is possible to initiate the attack remotely. The exploit is...

EUVD-2026-21694

A vulnerability was determined in FoundationAgents MetaGPT up to 0.8.1. The impacted element is the function evaluateCode of the file metagpt/environment/minecraft/mineflayer/index.js of the component Mineflayer HTTP API. Executing a manipulation can lead to cross-site request forgery. The attack...

PT-2026-32144

Name of the Vulnerable Software and Affected Versions FoundationAgents MetaGPT versions up to 0.8.1 Description A security flaw exists in FoundationAgents MetaGPT versions up to 0.8.1. The decode image function within the metagpt/utils/common.py file is susceptible to server-side request forgery...

Beyond Static Sandboxing: Learned Capability Governance for Autonomous AI Agents

Autonomous AI agents built on open-source runtimes such as OpenClaw expose every available tool to every session by default, regardless of the task. A summarization task receives the same shell execution, subagent spawning, and credential access capabilities as a code deployment task, a 15x...

EUVD-2026-21513

PraisonAIAgents: SSRF via unvalidated URL in webcrawl httpx fallback...

Permissive Cross-domain Policy with Untrusted Domains

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Permissive Cross-domain Policy with Untrusted Domains in the POST /agui endpoint due to the absence of authentication and the use of a...

Information Exposure

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Information Exposure via the subprocess module. An attacker can access sensitive environment variables, including API keys and credentials, ...

Directory Traversal

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Directory Traversal via the listfiles function when the pattern parameter is not properly validated before being passed to Path.glob. An...

Exposure of Sensitive Information Through Environmental Variables

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 Information Through Environmental Variables in the executecommand function, where environment variables within command...

Missing Authentication for Critical Function

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Missing Authentication for Critical Function via the listagents function. An attacker can access sensitive agent names, roles, and partial...

PraisonAI: Unauthenticated Information Disclosure of Agent Instructions via /api/agents in AgentOS

Summary The AgentOS deployment platform exposes a GET /api/agents endpoint that returns agent names, roles, and the first 100 characters of agent system instructions to any unauthenticated caller. The AgentOS FastAPI application has no authentication middleware, no API key validation, and default...

GHSA-PM96-6XPR-978X PraisonAI: Unauthenticated Information Disclosure of Agent Instructions via /api/agents in AgentOS

Summary The AgentOS deployment platform exposes a GET /api/agents endpoint that returns agent names, roles, and the first 100 characters of agent system instructions to any unauthenticated caller. The AgentOS FastAPI application has no authentication middleware, no API key validation, and default...

EUVD-2026-21170

PraisonAIAgents has SSRF and Local File Read via Unvalidated URLs in webcrawl Tool...

EUVD-2026-21164

PraisonAIAgents: Arbitrary File Read via readskillfile Missing Workspace Boundary and Approval Gate...

Missing Authorization

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Missing Authorization via the readskillfile function. An attacker can access sensitive files on the filesystem by supplying arbitrary paths ...

Command Injection

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Command Injection in the subprocess.run function due to passing user-controlled input directly to the shell with shell=True and without any...

CVE-2026-40160

PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, webcrawl's httpx fallback path passes user-supplied URLs directly to httpx.AsyncClient.get with followredirects=True and no host validation. An LLM agent tricked into crawling an internal URL can reach cloud metadata endpoints...