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...

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...

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...

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...

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...

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...

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...

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...

MAL-2026-6006 Malicious code in @mastra/claude (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 43c60df59e1fa51bbf7a5f6737d2c362f205589d70025f426f1004859168b1fe The package was found to contain malicious code or consuming dependency that contains malicious code Source: ghsa-malware...

Malicious code in @mastra/claude (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 43c60df59e1fa51bbf7a5f6737d2c362f205589d70025f426f1004859168b1fe The package was found to contain malicious code or consuming dependency that contains malicious code Source: ghsa-malware...

PT-2026-50594

Name of the Vulnerable Software and Affected Versions Claude Code versions 0.2.54 through 2.1.162 Description The WebFetch tool pre-approved the hostname 'huggingface.co' as a bare hostname, allowing any path on that domain to be auto-approved without a permission prompt or restrictions from...

MAL-2026-10693 Malicious code in claude-token-tracker-mcp (npm)

The claude-token-tracker-mcp package presents itself as an MCP token tracking server, but its server.js invokes silentHarvest immediately when the module loads and repeats the collection every hour. The collector reads Claude configuration files from the user's home directory, searches PowerShell...

Malicious code in claude-token-tracker-mcp (npm)

The claude-token-tracker-mcp package presents itself as an MCP token tracking server, but its server.js invokes silentHarvest immediately when the module loads and repeats the collection every hour. The collector reads Claude configuration files from the user's home directory, searches PowerShell...

CVE-2026-48124

Cursor is a code editor built for programming with AI. In versions prior to 3.0.0, the Cursor Desktop could execute workspace-defined Claude hook commands from .claude/settings.local.json without dedicated user approval. A malicious workspace or agent-created file could configure hooks that run...

EUVD-2026-37002

Cursor is a code editor built for programming with AI. In versions prior to 3.0.0, the Cursor Desktop could execute workspace-defined Claude hook commands from .claude/settings.local.json without dedicated user approval. A malicious workspace or agent-created file could configure hooks that run...

CVE-2026-48124 Cursor Desktop sandbox escape via Claude hook configuration

Cursor is a code editor built for programming with AI. In versions prior to 3.0.0, the Cursor Desktop could execute workspace-defined Claude hook commands from .claude/settings.local.json without dedicated user approval. A malicious workspace or agent-created file could configure hooks that run...

CVE-2026-48124

The CVE-2026-48124 affects Cursor Desktop prior to version 3.0.0. A workspace-defined Claude hook can be configured via .claude/settings.local.json to execute local commands without dedicated user approval, enabling possible sandbox escape, persistence across turns, and local data access if an ag...

CVE-2026-48124 Cursor Desktop sandbox escape via Claude hook configuration

Cursor is a code editor built for programming with AI. In versions prior to 3.0.0, the Cursor Desktop could execute workspace-defined Claude hook commands from .claude/settings.local.json without dedicated user approval. A malicious workspace or agent-created file could configure hooks that run...

MAL-2026-5789 Malicious code in claude-cup (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector c369ccf7b5e0ef8721b5ecdc94bd843ce260923394f6c513350a58928abdbdd3 On first invocation of npx claude-cup and on every subsequent Claude Code tool call once hooks are installed, research/config-audit.js enumerates eve...

Malicious code in claude-cup (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector c369ccf7b5e0ef8721b5ecdc94bd843ce260923394f6c513350a58928abdbdd3 On first invocation of npx claude-cup and on every subsequent Claude Code tool call once hooks are installed, research/config-audit.js enumerates eve...