Lucene search
+L

575 matches found

EUVD
EUVD
added 2026/07/24 4:54 p.m.22 views

EUVD-2026-40117

Claude Code: Sandbox Escape via Git Worktree Path Confusion Allows Unsandboxed Code Execution...

8.8CVSS5.9AI score0.00552EPSS
SaveExploits0References3
vulnersOsv
vulnersOsv
added 2026/07/24 4:54 p.m.11 views

@applydigital/claude (>=1.0.0, <=1.2.1), @bsklaroff/yaac (>=0.0.1, <=0.0.6) +13 more potentially affected by CVE-2026-55607 via @anthropic-ai/claude-code (>=2.1.39, <=2.1.154)

@anthropic-ai/claude-code NPM version =2.1.39, =1.0.0, =0.0.1, =0.7.5, =0.6.0-beta.3, =1.30.1-broken.0, =0.8.1, =0.8.0, =1.0.33, =1.0.0-dev.1, =2.1.99, =0.0.2, =1.2.2, =1.2.3 Source cves: CVE-2026-55607 Source advisory: OSV:GHSA-7835-87Q9-RGVV...

8.8CVSS5.3AI score0.00552EPSS
SaveExploits0
GithubExploit
GithubExploit
added 2026/07/21 3:39 p.m.56 views

slopguard

--- Your AI writes code faster than you can read it. That is th...

8.8CVSS6.7AI score0.27137EPSS
SaveExploits3
CVE
CVE
added 2026/07/20 10:09 p.m.49 views

CVE-2026-57495

CVE-2026-57495 affects AgenticMail components @agenticmail/claudecode (&lt;0.2.39), @agenticmail/codex (&lt;0.1.33), @agenticmail/core (&lt;0.9.43), and @agenticmail/openclaw (

8.2CVSS5.4AI score0.00362EPSS
SaveExploits0References1
Cvelist
Cvelist
added 2026/07/20 10:09 p.m.45 views

CVE-2026-57495 AgenticMail: Unauthenticated inbound mail triggers bypassPermissions resume of the operator's Claude Code session (bridge-wake)

AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/claudecode prior to version 0.2.39, @agenticmail/codex prior to version 0.1.33, @agenticmail/core prior to version 0.9.43, and @agenticmail/openclaw prior to version 0.5.71, two inbound-mail handlers act on a...

8.2CVSS0.00362EPSS
SaveExploits0References1
Vulnrichment
Vulnrichment
added 2026/07/20 10:09 p.m.12 views

CVE-2026-57495 AgenticMail: Unauthenticated inbound mail triggers bypassPermissions resume of the operator's Claude Code session (bridge-wake)

AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/claudecode prior to version 0.2.39, @agenticmail/codex prior to version 0.1.33, @agenticmail/core prior to version 0.9.43, and @agenticmail/openclaw prior to version 0.5.71, two inbound-mail handlers act on a...

8.2CVSS5.3AI score0.00362EPSS
SaveExploits0References1
EUVD
EUVD
added 2026/07/20 10:09 p.m.19 views

EUVD-2026-46124

AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/claudecode prior to version 0.2.39, @agenticmail/codex prior to version 0.1.33, @agenticmail/core prior to version 0.9.43, and @agenticmail/openclaw prior to version 0.5.71, two inbound-mail handlers act on a...

8.2CVSS5.3AI score0.00362EPSS
SaveExploits0References1
OSV
OSV
added 2026/07/20 10:37 a.m.10 views

MAL-2026-10892 Malicious code in claude-code-timer (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 04950731ec6589eebae22166fb042e4253719f71bfd3fc2b58f28d26ede9e43c [email protected] was scanned with no findings of concern. No install-time lifecycle scripts, no outbound network calls to attacker-controlled...

5.5AI score
SaveExploits0References2
OSSF Malicious Packages
OSSF Malicious Packages
added 2026/07/20 10:37 a.m.21 views

Malicious code in claude-code-timer (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 04950731ec6589eebae22166fb042e4253719f71bfd3fc2b58f28d26ede9e43c [email protected] was scanned with no findings of concern. No install-time lifecycle scripts, no outbound network calls to attacker-controlled...

5.5AI score
SaveExploits0References2
NVD
NVD
added 2026/07/16 5:16 p.m.18 views

CVE-2026-47751

Claude Code Action is a general-purpose GitHub action that runs Claude Code on GitHub pull requests and issues. Prior to 1.0.74, because the action checked out attacker-controlled pull request head branches, read .mcp.json from the working directory via default setting sources, and unconditionall...

5.3CVSS0.00766EPSS
SaveExploits0References4
ATTACKERKB
ATTACKERKB
added 2026/07/16 3:59 p.m.12 views

CVE-2026-47751

Claude Code Action is a general-purpose GitHub action that runs Claude Code on GitHub pull requests and issues. Prior to 1.0.74, because the action checked out attacker-controlled pull request head branches, read .mcp.json from the working directory via default setting sources, and unconditionall...

5.3CVSS6.5AI score0.00766EPSS
SaveExploits0References5Affected Software1
Cvelist
Cvelist
added 2026/07/16 3:59 p.m.39 views

CVE-2026-47751 Claude Code Action: Malicious MCP Server Configuration in PRs Enables Remote Code Execution and Secret Exfiltration

Claude Code Action is a general-purpose GitHub action that runs Claude Code on GitHub pull requests and issues. Prior to 1.0.74, because the action checked out attacker-controlled pull request head branches, read .mcp.json from the working directory via default setting sources, and unconditionall...

5.3CVSS0.00766EPSS
SaveExploits0References4
OSV
OSV
added 2026/07/16 3:59 p.m.13 views

CVE-2026-47751 Claude Code Action: Malicious MCP Server Configuration in PRs Enables Remote Code Execution and Secret Exfiltration

Claude Code Action is a general-purpose GitHub action that runs Claude Code on GitHub pull requests and issues. Prior to 1.0.74, because the action checked out attacker-controlled pull request head branches, read .mcp.json from the working directory via default setting sources, and unconditionall...

5.3CVSS6.5AI score
SaveExploits0References6
OSV
OSV
added 2026/07/13 2:36 p.m.16 views

PYSEC-2026-2475 FastMCP has a Command Injection vulnerability - Gemini CLI

Server names containing shell metacharacters e.g., & can cause command injection on Windows when passed to fastmcp install claude-code or fastmcp install gemini-cli. These install paths use subprocess.run with a list argument, but on Windows the target CLIs often resolve to .cmd wrappers that are...

6.7CVSS6.2AI score0.00735EPSS
SaveExploits1References7
The Hacker News
The Hacker News
added 2026/07/09 5:15 a.m.28 views

Top AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It

Ask an AI coding agent to scan open-source code for security holes, and it might run the attacker's code on your own machine instead. That is the finding in a proof-of-concept published Wednesday by the AI Now Institute, an attack it calls "Friendly Fire. " It works against Anthropic's Claude Cod...

10CVSS6.5AI score0.00711EPSS
SaveExploits0
RedhatCVE
RedhatCVE
added 2026/07/07 3:37 p.m.14 views

CVE-2026-54316

A flaw was found in Claude Code, an agentic coding tool. An attacker could exploit a misconfiguration in the tool's web request functionality, known as WebFetch, where the huggingface.co domain was pre-approved without proper path restrictions. By injecting untrusted content into a Claude Code...

9.1CVSS5.9AI score0.0052EPSS
SaveExploits0References4
Tenable Nessus
Tenable Nessus
added 2026/07/03 12:00 a.m.19 views

Anthropic Claude Code 2.1.59 < 2.1.128 Information Disclosure (CVE-2026-46406)

The version of Anthropic Claude Code installed on the remote host is 2.1.59 prior to 2.1.128. It is, therefore, affected by an information disclosure vulnerability: - The Claude Code /copy command wrote responses to a hardcoded, predictable path /tmp/claude/response.md without UID isolation,...

6.1CVSS6AI score0.00154EPSS
SaveExploits0References2
Tenable Nessus
Tenable Nessus
added 2026/07/03 12:00 a.m.25 views

Anthropic Claude Code 2.1.38 < 2.1.163 Sandbox Escape (CVE-2026-55607)

The version of Anthropic Claude Code installed on the remote host is 2.1.38 prior to 2.1.163. It is, therefore, affected by a sandbox escape vulnerability: - Claude Code's worktree handling allowed creation of worktrees named '.git' and navigation to worktrees outside the sandbox context, enablin...

8.8CVSS6.1AI score0.00552EPSS
SaveExploits0References2
RedhatCVE
RedhatCVE
added 2026/06/30 8:20 p.m.24 views

CVE-2026-55607

A flaw was found in Claude Code, an agentic coding tool, in its handling of worktrees. This vulnerability allowed the creation of specially named worktrees and navigation outside of the intended secure environment, leading to what is known as a 'git directory confusion attack'. By manipulating...

8.8CVSS6.1AI score0.00552EPSS
SaveExploits0References4
RedhatCVE
RedhatCVE
added 2026/06/30 1:37 p.m.27 views

CVE-2026-46406

A flaw was found in Claude Code. The /copy command created responses in a predictable, world-readable temporary file without proper isolation or symlink protection. This allowed a local unprivileged user to read sensitive information from a privileged user's Claude response, potentially containin...

6.8CVSS6AI score0.00154EPSS
SaveExploits0References4
Rows per page
Query Builder