UNIX Symbolic Link (Symlink) Following

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to UNIX Symbolic Link Symlink Following via the agents.create and agents.update processes. An attacker can append arbitrary content to files outside the intended workspace by planting a...

OpenClaw: Symlink Traversal via IDENTITY.md appendFile in agents.create/update (Incomplete Fix for CVE-2026-32013)

Summary The patch for CVE-2026-32013 introduced symlink resolution and workspace boundary enforcement for agents.files.get and agents.files.set. However, two other handlers in the same file agents.create and agents.update still use raw fs.appendFile on the IDENTITY.md file without any symlink...

CVE-2026-4516

A vulnerability was found in Foundation Agents MetaGPT up to 0.8.1. This vulnerability affects unknown code of the file metagpt/actions/di/writeanalysiscode.py of the component DataInterpreter. The manipulation results in injection. It is possible to launch the attack remotely. The exploit has be...

CVE-2026-32013

OpenClaw versions prior to 2026.2.25 contain a symlink traversal vulnerability in the agents.files.get and agents.files.set methods that allows reading and writing files outside the agent workspace. Attackers can exploit symlinked allowlisted files to access arbitrary host files within gateway...

@grackle-ai/mcp has a workspace authorization bypass in its knowledge_search MCP tool

Impact The knowledgesearch and knowledgegetnode MCP tools are included in SCOPEDTOOLS visible to scoped agents but their handlers do not receive authContext and do not enforce workspace scoping. A scoped agent in Workspace A can supply an arbitrary workspaceId parameter to search or retrieve...

GHSA-647H-P824-99W7 @grackle-ai/mcp has a workspace authorization bypass in its knowledge_search MCP tool

Impact The knowledgesearch and knowledgegetnode MCP tools are included in SCOPEDTOOLS visible to scoped agents but their handlers do not receive authContext and do not enforce workspace scoping. A scoped agent in Workspace A can supply an arbitrary workspaceId parameter to search or retrieve...

Introducing Wiz Workflows: Your path to building a self healing cloud

Orchestrate customizable workflows with agents, enabling end-to-end discovery and response in Wiz...

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents through Skills, Plugins, and Watchers

Whitepaper called ClawKeeper: Comprehensive Safety Protection For OpenClaw Agents Through Skills, Plugins, And Watchers...

Governing AI agent behavior: Aligning user, developer, role, and organizational intent

AI agents increasingly perform tasks that involve reasoning, acting, and interacting with other systems. Building a trusted agent requires ensuring it operates within the correct boundaries and performs tasks consistent with its intended purpose. In practice, this requires aligning several layers...

5 Learnings from the First-Ever Gartner Market Guide for Guardian Agents

On February 25, 2026, Gartner published its inaugural Market Guide for Guardian Agents, marking an important milestone for this emerging category. For those unfamiliar with the various Gartner report types, “a Market Guide defines a market and explains what clients can expect it to do in the shor...

API Security for AI Agents: Why Protection Has Never Been More Important.

For years, a lot of risky APIs survived simply because they were hard to find. They weren’t documented. Only a handful of engineers knew the endpoints. And if an attacker wanted to abuse them, they had to spend real time reverse‑engineering traffic and guessing how things worked. That “security b...

‘Get Down! Get Down! They’re Gonna See Us!’: Six Months of Hiding From ICE

A family in Chicago has been terrified to leave their apartment. Agents could be anywhere...

Introducing Wiz Agents & Workflows: Security at the Speed of AI

A new security operating model powered by AI agents that removes bottlenecks and enables teams to act at the speed of AI...

CVE-2026-4516

A vulnerability was found in Foundation Agents MetaGPT up to 0.8.1. This vulnerability affects unknown code of the file metagpt/actions/di/writeanalysiscode.py of the component DataInterpreter. The manipulation results in injection. It is possible to launch the attack remotely. The exploit has be...

CVE-2026-4516 Foundation Agents MetaGPT DataInterpreter write_analysis_code.py injection

A vulnerability was found in Foundation Agents MetaGPT up to 0.8.1. This vulnerability affects unknown code of the file metagpt/actions/di/writeanalysiscode.py of the component DataInterpreter. The manipulation results in injection. It is possible to launch the attack remotely. The exploit has be...

CVE-2026-4515

A vulnerability has been found in Foundation Agents MetaGPT up to 0.8.1. This affects the function codegenerate of the file metagpt/ext/aflow/scripts/operator.py. The manipulation leads to code injection. It is possible to initiate the attack remotely. The exploit has been disclosed to the public...

CVE-2026-4515 Foundation Agents MetaGPT operator.py code_generate code injection

A vulnerability has been found in Foundation Agents MetaGPT up to 0.8.1. This affects the function codegenerate of the file metagpt/ext/aflow/scripts/operator.py. The manipulation leads to code injection. It is possible to initiate the attack remotely. The exploit has been disclosed to the public...

CVE-2026-4515

A vulnerability has been found in Foundation Agents MetaGPT up to 0.8.1. This affects the function codegenerate of the file metagpt/ext/aflow/scripts/operator.py. The manipulation leads to code injection. It is possible to initiate the attack remotely. The exploit has been disclosed to the public...

CVE-2026-4515

Foundation Agents MetaGPT up to 0.8.1 contains a code injection vulnerability in metagpt/ext/aflow/scripts/operator.py: function code_generate. The issue allows remote initiation and is associated with a PROOF-OF-CONCEPT exploit; exploitation status is indicated by the sources as disclosed public...

CVE-2026-32051

OpenClaw versions prior to 2026.3.1 contain an authorization mismatch vulnerability that allows authenticated callers with operator.write scope to invoke owner-only tool surfaces including gateway and cron through agent runs in scoped-token deployments. Attackers with write-scope access can perfo...