Lucene search
+L

650 matches found

attackerkb
attackerkb
•added 2026/06/23 5:06 p.m.•19 views

CVE-2026-54316

Claude Code is an agentic coding tool. From 0.2.54 until 2.1.163, because the hostname huggingface.co was pre-approved as a bare hostname for the WebFetch tool, any path on that domain—including attacker-controlled model repositories—was auto-approved without a permission prompt or being subject ...

6CVSS5.9AI score0.0052EPSS
SaveExploits0References2Affected Software1
CVE
CVE
•added 2026/06/23 5:06 p.m.•206 views

CVE-2026-54316

CVE-2026-54316 (Claude Code) affects Claude Code versions 0.2.54–2.1.162, fixed in 2.1.163. The WebFetch tool allowed any path on the pre-approved domain huggingface.co, enabling an attacker-controlled repository path to be fetched without prompts or --allowedTools restrictions. If an attacker ca...

9.1CVSS6.1AI score0.0052EPSS
SaveExploits0References1Affected Software1
Cvelist
Cvelist
•added 2026/06/23 5:06 p.m.•53 views

CVE-2026-54316 Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch

Claude Code is an agentic coding tool. From 0.2.54 until 2.1.163, because the hostname huggingface.co was pre-approved as a bare hostname for the WebFetch tool, any path on that domain—including attacker-controlled model repositories—was auto-approved without a permission prompt or being subject ...

6CVSS0.0052EPSS
SaveExploits0References1
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/06/23 12:00 a.m.•2 views

CVE-2026-54316: Permissive List of Allowed Inputs

Claude Code is an agentic coding tool. From 0.2.54 until 2.1.163, because the hostname huggingface.co was pre-approved as a bare hostname for the WebFetch tool, any path on that domain—including attacker-controlled model repositories—was auto-approved without a permission prompt or being subject ...

9.1CVSS6.1AI score0.0052EPSS
SaveExploits0References5
OSV
OSV
•added 2026/06/19 3:59 p.m.•24 views

MAL-2026-6228 Malicious code in base_parts_ai (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 07b0e2bcf47f6720470181fe18dda70621d52a4fb65fec395a87e14ec39c5219 When a user runs the package's jcc or jcx CLI, lib/aiutils.js polls https://jai.jaskle.cn/hm/hmpub/aicccfg for a newVer value and, if it differs from...

6.2AI score
SaveExploits0References2
Snyk
Snyk
•added 2026/06/18 6:35 p.m.•17 views

Unsafe Dependency Resolution

Overview @theia/ai-claude-code is a Theia - Claude Code Integration Affected versions of this package are vulnerable to Unsafe Dependency Resolution via the automatic loading of .prompts/.prompttemplate files in a workspace. An attacker can manipulate the AI agent's system instructions by...

8.8CVSS6.1AI score0.00507EPSS
SaveExploits0References2
Snyk
Snyk
•added 2026/06/18 6:35 p.m.•18 views

Unsafe Dependency Resolution

Overview @theia/ai-claude-code is a Theia - Claude Code Integration Affected versions of this package are vulnerable to Unsafe Dependency Resolution via the processing of workspace file and directory names in the AI chat. An attacker can cause the agent to execute attacker-controlled instructions...

8.8CVSS6.2AI score0.00507EPSS
SaveExploits0References2
Snyk
Snyk
•added 2026/06/18 6:35 p.m.•8 views

Insertion of Sensitive Information Into Sent Data

Overview @theia/ai-claude-code is a Theia - Claude Code Integration Affected versions of this package are vulnerable to Insertion of Sensitive Information Into Sent Data via the rendering of Markdown image tags in AI chat responses. An attacker can cause sensitive information from the workspace o...

6.7CVSS5.8AI score0.00312EPSS
SaveExploits0References2
OSV
OSV
•added 2026/06/18 5:21 p.m.•14 views

GHSA-FQ4X-789W-JG5H AgenticMail: Unauthenticated inbound mail triggers bypassPermissions resume of the operator's Claude Code session (bridge-wake)

Summary Two inbound-mail handlers act on a privileged effect without verifying that the sender is the operator, while a sibling handler in the same repo does. The higher-impact one: any external email routed to the bridge inbox causes the dispatcher to resume the operator's Claude Code session wi...

8.2CVSS5.8AI score0.00362EPSS
SaveExploits0References3
OSV
OSV
•added 2026/06/18 4:28 p.m.•21 views

MAL-2026-6133 Malicious code in panrouter (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 9fd8aaf176011a764d660ee547645c34815e959d39087519cd187c1ac1af2d53 panrouter is advertised as a 'Claude Code router' but on default invocation panrouter with no arguments it a installs and rewrites the user's Claude...

5.5AI score
SaveExploits0References2
vulnersOsv
vulnersOsv
•added 2026/06/17 6:06 p.m.•11 views

1shot (>=0.0.3, <=0.0.9), @4via6/relay (>=1.0.0, <=1.1.3) +251 more potentially affected by CVE-2026-54316 via @anthropic-ai/claude-code (>=0.2.126, <=2.1.154)

@anthropic-ai/claude-code NPM version =0.2.126, =0.0.3, =1.0.0, =2.1.0, =0.1.18, =1.0.0, =0.4.0, =1.0.0, =0.2.3, =0.0.1, =0.0.1, =0.0.55, =0.0.69 and more Source cves: CVE-2026-54316 Source advisory: SNYK:JS-ANTHROPICAICLAUDECODE-17391874...

9.1CVSS5.7AI score0.0052EPSS
SaveExploits0
Snyk
Snyk
•added 2026/06/17 6:06 p.m.•17 views

Covert Storage Channel

Overview @anthropic-ai/claude-code is an Use Claude, Anthropic's AI assistant, right from your terminal. Claude can understand your codebase, edit files, run terminal commands, and handle entire workflows for you. Affected versions of this package are vulnerable to Covert Storage Channel via the...

9.1CVSS5.9AI score0.0052EPSS
SaveExploits0References3
Github Security Blog
Github Security Blog
•added 2026/06/17 6:06 p.m.•35 views

Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch

Because the hostname huggingface.co was pre-approved as a bare hostname for the WebFetch tool, any path on that domain—including attacker-controlled model repositories—was auto-approved without a permission prompt or being subject to --allowedTools restrictions. An attacker able to inject untrust...

9.1CVSS6AI score0.0052EPSS
SaveExploits0References3Affected Software1
vulnersOsv
vulnersOsv
•added 2026/06/17 6:06 p.m.•10 views

1shot (>=0.0.3, <=0.0.9), @4via6/relay (>=1.0.0, <=1.1.3) +251 more potentially affected by CVE-2026-54316 via @anthropic-ai/claude-code (>=0.2.126, <=2.1.154)

@anthropic-ai/claude-code NPM version =0.2.126, =0.0.3, =1.0.0, =2.1.0, =0.1.18, =1.0.0, =0.4.0, =1.0.0, =0.2.3, =0.0.1, =0.0.1, =0.0.55, =0.0.69 and more Source cves: CVE-2026-54316 Source advisory: OSV:GHSA-FG94-H982-F3MM...

9.1CVSS5.7AI score0.0052EPSS
SaveExploits0
OSV
OSV
•added 2026/06/17 6:06 p.m.•29 views

GHSA-FG94-H982-F3MM Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch

Because the hostname huggingface.co was pre-approved as a bare hostname for the WebFetch tool, any path on that domain—including attacker-controlled model repositories—was auto-approved without a permission prompt or being subject to --allowedTools restrictions. An attacker able to inject untrust...

9.1CVSS5.6AI score0.0052EPSS
SaveExploits0References3
Positive Technologies
Positive Technologies
•added 2026/06/17 12:00 a.m.•31 views

PT-2026-50594

Name of the Vulnerable Software and Affected Versions Claude Code versions 0.2.54 through 2.1.162 Description Claude Code, an agentic coding tool, contains an issue where the hostname huggingface.co was pre-approved for the WebFetch tool. This allowed any path on that domain, including...

9.1CVSS6.3AI score0.0052EPSS
SaveExploits0References12
HackRead
HackRead
•added 2026/06/11 1:20 p.m.•44 views

Hackers Use Fake Claude Code Guide and AI PDFs to Spread AsyncRAT Malware

Hackers are using fake Claude Code guide and AI PDFs to spread AsyncRAT malware via Windows attack using PowerShell and Defender exclusions...

5.4AI score
SaveExploits0
OSV
OSV
•added 2026/06/11 7:16 a.m.•21 views

MAL-2026-5592 Malicious code in 0x2ai-demo6 (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 0f4a43a40af9e707d98ed55406b0ff32dccaad352fccf5d1eaaca41b9959d924 On npm install, scripts/postinstall.cjs writes .mcp.json into the installer's working directory INITCWD wiring Claude Code to a packaged MCP server...

5.5AI score
SaveExploits0References1
OSSF Malicious Packages
OSSF Malicious Packages
•added 2026/06/11 7:16 a.m.•26 views

Malicious code in 0x2ai-demo6 (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 0f4a43a40af9e707d98ed55406b0ff32dccaad352fccf5d1eaaca41b9959d924 On npm install, scripts/postinstall.cjs writes .mcp.json into the installer's working directory INITCWD wiring Claude Code to a packaged MCP server...

5.5AI score
SaveExploits0References1
OSSF Malicious Packages
OSSF Malicious Packages
•added 2026/06/11 7:16 a.m.•26 views

Malicious code in 0x2ai-demo7x (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector c7e956073a7db6057e4d42af462dba0299152ca992c113d74c715e90574d0efb On npm install, scripts/postinstall.cjs copies the package's payload/ tree into the installer's project root process.env.INITCWD, placing...

5.5AI score
SaveExploits0References1
Rows per page
Query Builder