OpenClaw (npm package openclaw) versions >= 2026.3.22 and < 2026.8.1 contain an approval-bypass flaw in the exec approval policy: the policy could trust a command-running wrapper without inspecting the command carried in its arguments. After an operator allowlisted or permanently approved a benign wrapper invocation, a later agent turn could substitute an arbitrary inner command and execute it with the OpenClaw processs host privileges without a further approval prompt. Exploitation requires the relevant wrapper to resolve on the host and a prior operator decision allowing that wrapper. Transparent shell carriers and opaque utilities such as process monitors, tracers, namespace tools, and proxy wrappers were affected through related trust-resolution gaps. Fixed in 2026.8.1.
Weakness
The product constructs a string for a command to be executed by a separate component in another control sphere, but it does not properly delimit the intended arguments, options, or switches within that command string.
Extended Description
When creating commands using interpolation into a string, developers may assume that only the arguments/options that they specify will be processed. This assumption may be even stronger when the programmer has encoded the command in a way that prevents separate commands from being provided maliciously, e.g. in the case of shell metacharacters. When constructing the command, the developer may use whitespace or other delimiters that are required to separate arguments when the command. However, if an attacker can provide an untrusted input that contains argument-separating delimiters, then the resulting command will have more arguments than intended by the developer. The attacker may then be able to change the behavior of the command. Depending on the functionality supported by the extraneous arguments, this may have security-relevant consequences.
Potential Mitigations
- Assume all input is malicious. Use an “accept known good” input validation strategy, i.e., use a list of acceptable inputs that strictly conform to specifications. Reject any input that does not strictly conform to specifications, or transform it into something that does.
- When performing input validation, consider all potentially relevant properties, including length, type of input, the full range of acceptable values, missing or extra inputs, syntax, consistency across related fields, and conformance to business rules. As an example of business rule logic, “boat” may be syntactically valid because it only contains alphanumeric characters, but it is not valid if the input is only expected to contain colors such as “red” or “blue.”
- Do not rely exclusively on looking for malicious or malformed inputs. This is likely to miss at least one undesirable input, especially if the code’s environment changes. This can give attackers enough room to bypass the intended validation. However, denylists can be useful for detecting potential attacks or determining which inputs are so malformed that they should be rejected outright.
- Inputs should be decoded and canonicalized to the application’s current internal representation before being validated (CWE-180, CWE-181). Make sure that your application does not inadvertently decode the same input twice (CWE-174). Such errors could be used to bypass allowlist schemes by introducing dangerous inputs after they have been checked. Use libraries such as the OWASP ESAPI Canonicalization control.
- Consider performing repeated canonicalization until your input does not change any more. This will avoid double-decoding and similar scenarios, but it might inadvertently modify inputs that are allowed to contain properly-encoded dangerous content.
Related Attack Patterns
- https://cwe.mitre.org/data/definitions/137.html
- https://cwe.mitre.org/data/definitions/174.html
- https://cwe.mitre.org/data/definitions/41.html
- https://cwe.mitre.org/data/definitions/460.html
- https://cwe.mitre.org/data/definitions/88.html