HighVulnerabilityLLM-specific
GHSA-v3qc-wrwx-j3pw: OpenClaw: Agentic Consent Bypass — LLM Agent Can Silently Disable Exec Approval via `config.patch`
- Identifier
- GHSA-v3qc-wrwx-j3pw
- Published
- Record updated
- Affected
- openclaw <= 2026.3.24
- Fixed in
- 2026.3.28
- released March 28, 2026, 5 days before disclosure
Summary
OpenClaw's openclaw npm package, versions <=2026.3.24, lets an LLM agent silently disable exec approval through the config.patch function, bypassing user consent for command execution. Maintainers fixed it in commit 76411b2afc4ae721e36c12e0ea24fd23e2fed61e, shipped in v2026.3.28, and rate the issue high severity.
Mitigation
Fixed in v2026.3.28 (commit 76411b2afc4ae721e36c12e0ea24fd23e2fed61e); upgrade openclaw to >= 2026.3.28.
Topics
Related items
- CriticalGHSA-9x8x-crjq-g64h: Jupyter MCP Server: Browser DNS rebinding can hijack the Jupyter backend through management routesSimilar attack · GitHub Advisory Database
- HighGHSA-24pw-rf5p-mgp7: Jupyter MCP Server: Unauthenticated management routes can hijack the Jupyter backend in standalone HTTP modeSimilar attack · GitHub Advisory Database
- HighGHSA-m932-63jc-4jqq: k8s-mcp-server: Missing authentication on default SSE/HTTP transport allows unauthenticated Kubernetes tool executionSimilar attack · GitHub Advisory Database
- HighGHSA-3mgh-93r5-r7jf: CodeWhale: exec_shell parallel-readonly classifier auto-approves fd/rg/git grep exec flags enabling silent RCESimilar attack · GitHub Advisory Database
- HighGHSA-qx49-fqc8-xw99: Model Context Protocol Python SDK: OAuth client could send credentials to an authorization server chosen by the MCP serverSimilar attack · GitHub Advisory Database