Lucene search
+L

120 matches found

Github Security Blog
Github Security Blog
added 2026/08/17 9:56 p.m.9 views

chrome-devtools-mcp: validatePath() does not canonicalize symlinks before enforcing roots

Summary I originally reported this through Google Bug Hunters. The Google Bug Hunters team said this is in OSS VRP scope but not reward-eligible due to the project tier, and asked me to file an issue or PR directly with this repository. I am reporting it privately here first because it is an...

6.1CVSS5.5AI score0.00107EPSS
SaveExploits1References6Affected Software1
EUVD
EUVD
added 2026/08/06 2:24 p.m.10 views

EUVD-2026-53936

OpenChamber 1.11.7 contains a path traversal vulnerability in the file-serving endpoints /api/fs/read, /api/fs/stat, and /api/fs/raw that allows unauthenticated remote attackers to read arbitrary files by supplying the allowOutsideWorkspace=true query parameter alongside an absolute path, bypassi...

9.3CVSS5.7AI score0.01899EPSS
SaveExploits0References3
Cvelist
Cvelist
added 2026/08/06 2:24 p.m.28 views

CVE-2026-53976 OpenChamber 1.11.7 Path Traversal File Read via allowOutsideWorkspace Parameter

OpenChamber 1.11.7 contains a path traversal vulnerability in the file-serving endpoints /api/fs/read, /api/fs/stat, and /api/fs/raw that allows unauthenticated remote attackers to read arbitrary files by supplying the allowOutsideWorkspace=true query parameter alongside an absolute path, bypassi...

9.3CVSS0.01899EPSS
SaveExploits0References3
OSV
OSV
added 2026/07/23 11:41 a.m.13 views

PYSEC-2026-3512 PraisonAI Code agent tools fail open without a workspace boundary

PraisonAI Code agent tools fail open without a workspace boundary Summary PraisonAI Code's agent-compatible CODETOOLS wrappers keep a global workspace root initialized to None. If an application uses CODETOOLS, codereadfile, codesearchreplace, or codeapplydiff before calling setworkspace, the...

7.3CVSS5.6AI score
SaveExploits0References5
OSV
OSV
added 2026/07/23 11:41 a.m.11 views

PYSEC-2026-3527 PraisonAI: Arbitrary File Read via `@file:` Mention Path Traversal

Summary The MentionsParser in src/praisonai-agents/praisonaiagents/tools/mentions.py processes @file: mentions in agent prompts by reading arbitrary files from the filesystem. When a file path is not found relative to the workspace, the parser falls back to using the path as an absolute path...

7.5CVSS5.7AI score
SaveExploits0References5
OSV
OSV
added 2026/07/13 2:36 p.m.10 views

PYSEC-2026-2949 PraisonAIAgents: Arbitrary File Read via read_skill_file Missing Workspace Boundary and Approval Gate

Summary readskillfile in skilltools.py allows reading arbitrary files from the filesystem by accepting an unrestricted skillpath parameter. Unlike filetools.readfile which enforces workspace boundary confinement, and unlike runskillscript which requires critical-level approval, readskillfile has...

6.2CVSS6.2AI score0.00234EPSS
SaveExploits1References5
OSV
OSV
added 2026/07/13 2:36 p.m.12 views

PYSEC-2026-2944 PraisonAIAgents: Path Traversal via Unvalidated Glob Pattern in list_files Bypasses Workspace Boundary

Summary The listfiles tool in FileTools validates the directory parameter against workspace boundaries via validatepath, but passes the pattern parameter directly to Path.glob without any validation. Since Python's Path.glob supports .. path segments, an attacker can use relative path traversal i...

5.3CVSS6.2AI score0.00311EPSS
SaveExploits1References5
OSV
OSV
added 2026/06/29 11:50 a.m.18 views

PYSEC-2026-475 PraisonAI Vulnerable to Arbitrary File Write / Path Traversal in Action Orchestrator

The Action Orchestrator feature contains a Path Traversal vulnerability that allows an attacker or compromised agent to write to arbitrary files outside of the configured workspace directory. By supplying relative path segments ../ in the target path, malicious actions can overwrite sensitive...

9CVSS6.2AI score0.00306EPSS
SaveExploits1References6
NVD
NVD
added 2026/06/25 7:16 p.m.15 views

CVE-2026-50548

Cursor is a code editor built for programming with AI. Prior to 3.0, Cursor runs agent terminal commands in a sandbox by default, and the sandbox grants write access to the command's working directory. A flaw was identified in how the agent could modify the workingdirectory parameter, which could...

9.8CVSS0.00957EPSS
SaveExploits0References1
Vulnrichment
Vulnrichment
added 2026/06/24 9:29 p.m.10 views

CVE-2026-53766 chrome-devtools-mcp: validatePath() does not canonicalize symlinks before enforcing roots

Chrome DevTools for agents chrome-devtools-mcp lets your coding agent control and inspect a live Chrome browser. From 0.24.0 until 1.1.0, McpContext.validatePath enforces workspace roots by checking whether path.resolvefilePath textually falls under one of the configured root paths. path.resolve...

6.1CVSS5.8AI score0.00107EPSS
SaveExploits1References1
CVE
CVE
added 2026/06/24 9:29 p.m.42 views

CVE-2026-53766

CVE-2026-53766 affects Chrome DevTools for agents (chrome-devtools-mcp). The issue arises because MCP's validatePath() uses path.resolve() to enforce workspace roots; path.resolve() does not canonicalize symbolic links, allowing a symlink within a configured root to point to a file outside that r...

6.1CVSS5.8AI score0.00107EPSS
SaveExploits1References1Affected Software1
ATTACKERKB
ATTACKERKB
added 2026/06/24 9:29 p.m.10 views

CVE-2026-53766

Chrome DevTools for agents chrome-devtools-mcp lets your coding agent control and inspect a live Chrome browser. From 0.24.0 until 1.1.0, McpContext.validatePath enforces workspace roots by checking whether path.resolvefilePath textually falls under one of the configured root paths. path.resolve...

6.1CVSS5.8AI score0.00107EPSS
SaveExploits1References2Affected Software1
OSV
OSV
added 2026/06/24 9:29 p.m.9 views

CVE-2026-53766 chrome-devtools-mcp: validatePath() does not canonicalize symlinks before enforcing roots

Chrome DevTools for agents chrome-devtools-mcp lets your coding agent control and inspect a live Chrome browser. From 0.24.0 until 1.1.0, McpContext.validatePath enforces workspace roots by checking whether path.resolvefilePath textually falls under one of the configured root paths. path.resolve...

6.1CVSS5.9AI score
SaveExploits0References3
EUVD
EUVD
added 2026/06/23 4:03 p.m.17 views

EUVD-2026-38489

Missing symlink validation in Language Servers for AWS may allow an arbitrary file write outside of the workspace trust boundary. This may occur when a local user opens a workspace with a maliciously crafted symlink that resolves to a file path outside the workspace trust boundary. To remediate...

8.5CVSS6AI score0.00255EPSS
SaveExploits0References2
CVE
CVE
added 2026/06/23 4:03 p.m.41 views

CVE-2026-12958

CVE-2026-12958 affects Language Servers for AWS due to missing symlink validation, allowing arbitrary file write outside the workspace trust boundary when a user opens a workspace containing a crafted symlink. The issue is reported across multiple sources (CVE entry, NVD, and related databases). ...

8.5CVSS6AI score0.00255EPSS
SaveExploits0References2
Github Security Blog
Github Security Blog
added 2026/06/18 2:27 p.m.19 views

PraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validation

Summary The multiedit tool in src/praisonai/praisonai/tools/multiedit.py allows LLM-controlled arbitrary file read and write without any path validation, workspace boundary check, or protected path guard. This enables an attacker who can influence agent tool arguments via crafted prompts, user...

5.8AI score
SaveExploits0References2Affected Software1
OSV
OSV
added 2026/06/18 2:27 p.m.30 views

GHSA-29W3-P9W9-WC47 PraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validation

Summary The multiedit tool in src/praisonai/praisonai/tools/multiedit.py allows LLM-controlled arbitrary file read and write without any path validation, workspace boundary check, or protected path guard. This enables an attacker who can influence agent tool arguments via crafted prompts, user...

9.1CVSS5.9AI score
SaveExploits0References2
Snyk
Snyk
added 2026/06/18 1:59 p.m.20 views

Incorrect Authorization

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

8.5CVSS5.8AI score
SaveExploits0References3
OSV
OSV
added 2026/06/18 1:59 p.m.14 views

GHSA-GCQ3-MFVH-3X25 PraisonAI Code agent tools fail open without a workspace boundary

PraisonAI Code agent tools fail open without a workspace boundary Summary PraisonAI Code's agent-compatible CODETOOLS wrappers keep a global workspace root initialized to None. If an application uses CODETOOLS, codereadfile, codesearchreplace, or codeapplydiff before calling setworkspace, the...

7.3CVSS5.6AI score
SaveExploits0References2
Github Security Blog
Github Security Blog
added 2026/06/18 1:59 p.m.18 views

PraisonAI Code agent tools fail open without a workspace boundary

PraisonAI Code agent tools fail open without a workspace boundary Summary PraisonAI Code's agent-compatible CODETOOLS wrappers keep a global workspace root initialized to None. If an application uses CODETOOLS, codereadfile, codesearchreplace, or codeapplydiff before calling setworkspace, the...

5.6AI score
SaveExploits0References2Affected Software1
Rows per page
Query Builder