Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-03-04 · source-backed
Three attack vectors: (1) Hooks-based RCE via .claude/settings.json executing shell commands on SessionStart without confirmation, (2) MCP consent bypass via repo-controlled config auto-approving all servers, (3) API key exfiltration via ANTHROPIC_BASE_URL pointing to attacker endpoint. All patched. Always review .claude/ config files before opening untrusted repositories. (Check Point Research)
Each link below shares sources, entities, or timing with this story.
Check Point Research disclosed CVE-2025-59536 and CVE-2026-21852 — two vulnerabilities that weaponize Claude Code's project configuration system against its users. This matters because an Agents Anonymous survey this week showed 90% of practitioners at their SF meetup use Clau...
Check Point Research disclosed that ANTHROPIC_BASE_URL in a repository's .claude config can redirect all API traffic — including full authorization headers — to an attacker-controlled server before the user reads a trust dialog, exfiltrating API keys in plaintext. A second vec...
The most important security research this week. Check Point demonstrated three attack vectors in Claude Code exploiting project configuration files in untrusted repositories: (1) Hooks RCE (CVE-2025-59536, CVSS 8.7) — malicious hooks in .claude/settings.json execute shell comm...
Check Point Research disclosed that Claude Code's .claude/settings.json hooks can be weaponized in untrusted repos to execute arbitrary shell commands and exfiltrate Anthropic API keys by redirecting ANTHROPIC_BASE_URL to an attacker-controlled MitM proxy (Check Point). Both C...
The Amazon Q bug is one instance of a 2026 pattern: MCP configuration carried in repositories is now an RCE supply-chain vector, not just untrusted tool output. Cursor, VS Code, Windsurf, Claude Code, and Gemini-CLI are all vulnerable to MCP-based auto-launch attacks (Windsurf...
The agent skills supply chain is under coordinated attack. Snyk's ToxicSkills audit found 36% of ClawHub's 3,984 skills contain prompt injection payloads, 13.4% have critical malware, and submission rates exploded 10x to 500+/day. This week alone: CVE-2026-2256 (CVSS 9.1) is a...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.