@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...

Tego AI Discloses Second Claude Flaw in a Week: Hidden Link Silently Sends Files to Attackers

Tel Aviv, Israel, 24th July 2026, CyberNewswire...

Claude Cowork Flaw Could Let AI Agent Escape Its VM and Access Mac Files

Cybersecurity researchers have uncovered a sandbox escape vulnerability in Anthropic's Claude Cowork that makes it possible to break out of the confines of a Linux virtual machine VM within which the agent runs to read or write files anywhere on the Mac. Accomplish AI, which shared details of the...

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 (

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...

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...

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...

CVE-2026-46412 Malicious code in @beproduct/nestjs-auth (0.1.2 through 0.1.19) — Mini Shai-Hulud worm

@beproduct/nestjs-auth is a NestJS authentication module for BeProduct IDS Identity Server with OpenID Connect support. Between 2026-05-11 20:19 UTC and 22:56 UTC, an attacker used a compromised npm publish token to publish 18 malicious versions of @beproduct/nestjs-auth 0.1.2 through 0.1.19. The...

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...

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...

MAL-2026-10737 Malicious code in mmagrt (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector f7eddaa3f964de5ebd63c3272f8abe021b60402b5fde4d4437cc254c99a8211a The npm package advertises itself as a 'VPS routine scheduler' but ships prebuilt Rust binaries mmagrt and mmagrt-mcp for darwin-arm64, darwin-x64,...

Malicious code in @funny-booth/agent-core (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 6693129f8b6f8b6c2d52722ca7746d6ef3dd792476297fa3583d3956548eb2b4 The package ships heavily obfuscated runtime files dist/index.js, dist/launcher.js built with javascript-obfuscator. The MCP server registered as the...

MAL-2026-10711 Malicious code in @funny-booth/agent-core (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 6693129f8b6f8b6c2d52722ca7746d6ef3dd792476297fa3583d3956548eb2b4 The package ships heavily obfuscated runtime files dist/index.js, dist/launcher.js built with javascript-obfuscator. The MCP server registered as the...

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...

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...

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...

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...

MAL-2026-10629 Malicious code in ai-pro-sdk (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector b035f137addcf0118c3d042ece322d0fdde054e4ed283317d3b2adb309e38689 [email protected] is advertised as a Vercel AI SDK provider for Claude via the Claude Agent SDK, but the published tarball ships no code: package.json...

Malicious code in ai-pro-sdk (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector b035f137addcf0118c3d042ece322d0fdde054e4ed283317d3b2adb309e38689 [email protected] is advertised as a Vercel AI SDK provider for Claude via the Claude Agent SDK, but the published tarball ships no code: package.json...

PYSEC-2026-2676 Cortex has Untrusted Project Bootstrap Code Execution via `CLAUDE_PROJECT_DIR`

Untrusted Project Bootstrap Code Execution via CLAUDEPROJECTDIR Summary The Cortex MCP server neuro-cortex-memory treats the CLAUDEPROJECTDIR environment variable — automatically set by Claude Code to the currently open project directory — as a trusted Cortex developer checkout. When the...