CVE-2026-53855

OpenClaw before 2026.4.2 contains an inline-eval bypass vulnerability allowing authenticated operators to weaken strict allowlist checks via shell positional parameters. Attackers can combine allowlisted tools with shell positional arguments to place inline-eval content in shell carriers outside intended allowlist rules, enabling execution of unapproved shell-provided content.

OpenClaw before 2026.4.2 contains an inline-eval bypass vulnerability allowing authenticated operators to weaken strict allowlist checks via shell positional parameters. Attackers can combine allowlisted tools with shell positional arguments to place inline-eval content in shell carriers outside intended allowlist rules, enabling execution of unapproved shell-provided content.

Duplicate Advisory

This advisory has been withdrawn because it is a duplicate of GHSA-5cj2-3jr2-5h77. This link is maintained to preserve external references.

Original Description

OpenClaw before 2026.4.2 contains an inline-eval bypass vulnerability allowing authenticated operators to weaken strict allowlist checks via shell positional parameters. Attackers can combine allowlisted tools with shell positional arguments to place inline-eval content in shell carriers outside intended allowlist rules, enabling execution of unapproved shell-provided content.

Summary

Shell positional parameters could weaken strict inline-eval checks. In affected versions, a command request that combines allowlisted tools with shell positional arguments could place inline-eval content in a shell carrier not covered by the strict check.

This advisory is scoped to the named feature and configuration. It does not change OpenClaw's trusted-operator model: authenticated Gateway operators, installed plugins, and intentional local execution surfaces remain trusted unless a separate policy, approval, allowlist, sandbox, or auth boundary is crossed.

Impact

When the affected feature is enabled and reachable, this could run shell-provided content outside the intended allowlist rule. Practical impact depends on the operator's configuration and whether lower-trust input can reach that path.

Patched Versions

The first stable patched version is 2026.4.2.

Mitigations

avoid allowlisting shell carrier patterns and require approval for shell wrappers until patched. As general hardening, keep channel and tool allowlists narrow, avoid sharing one Gateway between mutually untrusted users, and disable the affected feature when it is not needed.

OpenClaw before 2026.4.2 contains an inline-eval bypass vulnerability allowing authenticated operators to weaken strict allowlist checks via shell positional parameters. Attackers can combine allowlisted tools with shell positional arguments to place inline-eval content in shell carriers outside intended allowlist rules, enabling execution of unapproved shell-provided content.

OpenClaw before 2026.4.2 contains an inline-eval bypass vulnerability allowing authenticated operators to weaken strict allowlist checks via shell positional parameters. Attackers can combine allowlisted tools with shell positional arguments to place inline-eval content in shell carriers outside intended allowlist rules, enabling execution of unapproved shell-provided content.

Duplicate Advisory

This advisory has been withdrawn because it is a duplicate of GHSA-5cj2-3jr2-5h77. This link is maintained to preserve external references.

Original Description

OpenClaw before 2026.4.2 contains an inline-eval bypass vulnerability allowing authenticated operators to weaken strict allowlist checks via shell positional parameters. Attackers can combine allowlisted tools with shell positional arguments to place inline-eval content in shell carriers outside intended allowlist rules, enabling execution of unapproved shell-provided content.

Summary

Shell positional parameters could weaken strict inline-eval checks. In affected versions, a command request that combines allowlisted tools with shell positional arguments could place inline-eval content in a shell carrier not covered by the strict check.

This advisory is scoped to the named feature and configuration. It does not change OpenClaw's trusted-operator model: authenticated Gateway operators, installed plugins, and intentional local execution surfaces remain trusted unless a separate policy, approval, allowlist, sandbox, or auth boundary is crossed.

Impact

When the affected feature is enabled and reachable, this could run shell-provided content outside the intended allowlist rule. Practical impact depends on the operator's configuration and whether lower-trust input can reach that path.

Patched Versions

The first stable patched version is 2026.4.2.

Mitigations

avoid allowlisting shell carrier patterns and require approval for shell wrappers until patched. As general hardening, keep channel and tool allowlists narrow, avoid sharing one Gateway between mutually untrusted users, and disable the affected feature when it is not needed.