CVE-2026-35570

OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Versions prior to 0.5.1 have a logic flaw in bashToolHasPermission inside src/tools/BashTool/bashPermissions.ts. When the sandbox auto-allow feature is active and no explicit deny rule is...

Access Control Bypass

Overview @gitlawb/openclaude is an OpenClaude opens coding-agent workflows to any LLM — OpenAI, Gemini, DeepSeek, Ollama, and 200+ models Affected versions of this package are vulnerable to Access Control Bypass via the bashToolHasPermission function. An attacker can access or modify files outsid...

EUVD-2026-23988

OpenClaude: Sandbox Bypass via Early-Exit Logic Flaw Allows Path Traversal...

OpenClaude: Sandbox Bypass via Early-Exit Logic Flaw Allows Path Traversal

A logic flaw exists in bashToolHasPermission inside src/tools/BashTool/bashPermissions.ts. When the sandbox auto-allow feature is active and no explicit deny rule is configured, the function returns an allow result immediately — before the path constraint filter checkPathConstraints is ever...

GHSA-M6RX-7PVW-2F73 OpenClaude: Sandbox Bypass via Early-Exit Logic Flaw Allows Path Traversal

A logic flaw exists in bashToolHasPermission inside src/tools/BashTool/bashPermissions.ts. When the sandbox auto-allow feature is active and no explicit deny rule is configured, the function returns an allow result immediately — before the path constraint filter checkPathConstraints is ever...

CVE-2026-35570

OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Versions prior to 0.5.1 have a logic flaw in bashToolHasPermission inside src/tools/BashTool/bashPermissions.ts. When the sandbox auto-allow feature is active and no explicit deny rule is...

CVE-2026-35570

OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Versions prior to 0.5.1 have a logic flaw in bashToolHasPermission inside src/tools/BashTool/bashPermissions.ts. When the sandbox auto-allow feature is active and no explicit deny rule is...

Incorrect Authorization

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Incorrect Authorization in the autoAllowSkills process. An attacker can execute unauthorized skills without operator approval by exploiting a skill-name collision when autoAllowSkills is...

OpenClaw's non-default autoAllowSkills setting could bypass on-miss exec prompt

Summary In openclaw versions up to and including 2026.2.22-2, a non-default exec-approval configuration could allow a skill-name collision to bypass an ask=on-miss prompt. When autoAllowSkills=true, a path-scoped executable such as ./skill-bin could resolve to basename skill-bin, satisfy the skil...

GHSA-7FF8-XJH3-MGH6 OpenClaw's non-default autoAllowSkills setting could bypass on-miss exec prompt

Summary In openclaw versions up to and including 2026.2.22-2, a non-default exec-approval configuration could allow a skill-name collision to bypass an ask=on-miss prompt. When autoAllowSkills=true, a path-scoped executable such as ./skill-bin could resolve to basename skill-bin, satisfy the skil...