Security readout for executives and security teams
Plain-English summary
OpenClaw 2026.3.1 can execute code that differs from what an operator approved. A local attacker could abuse command argument rewriting and a malicious script in the working directory. This is not reported as actively exploited, but it can affect confidentiality, integrity, and availability where OpenClaw runs trusted automation.
Executive priority
Treat as a scheduled but important patch for OpenClaw users. Prioritize environments where OpenClaw automates sensitive operations or where multiple users can write to automation directories. The issue is medium severity and not known exploited, but successful abuse could run unintended code.
Technical view
CVE-2026-29608 is a CWE-88 argument injection/command semantics issue in OpenClaw system.run node-host execution. argv rewriting can change command meaning after approval. A low-privileged local attacker, with user interaction and high complexity, may cause unintended code execution from the working directory. OpenClaw 2026.3.1 is listed as affected.
Likely exposure
Exposure appears limited to OpenClaw 2026.3.1 deployments using system.run node-host execution and operator approvals. Risk is higher where working directories are writable by lower-privileged users or contain untrusted project files. The source bundle lists default status as unaffected for other versions.
Exploitation context
No provided source reports active exploitation, and the CVE is not marked KEV. Exploitation is local, requires low privileges, high complexity, and operator interaction. The attacker must influence local scripts in the working directory so approved command text executes with changed semantics.
Researcher notes
The public description is concise and does not provide full reproduction detail. Analysis should focus on argv rewriting across approval boundaries in system.run node-host execution. Avoid assuming remote reachability or affected versions beyond OpenClaw 2026.3.1 unless confirmed by vendor sources.
Mitigation direction
- Upgrade OpenClaw from 2026.3.1 to 2026.3.2 or later per vendor guidance.
- Review the GitHub advisory and patch commit before deployment.
- Avoid running system.run workflows from untrusted or user-writable working directories.
- Restrict who can write files into OpenClaw automation working directories.
Validation and detection
- Inventory OpenClaw instances and identify version 2026.3.1.
- Confirm patched builds include the referenced GitHub commit or a vendor-approved release.
- Review system.run node-host workflows that rely on operator approval.
- Check whether automation working directories are writable by lower-privileged users.
- Review logs for unexpected local script execution around approval events.
Public sources used
Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.
Conservative CVE-to-ATT&CK context
These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.
ATT&CK lookup starting points
Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.
CWE-88: Command execution behavior lookup
Command injection weaknesses can lead defenders to review execution techniques and command interpreter telemetry. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
Open ATT&CK lookupCVE-2026-29608 mapping review
Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.
Open ATT&CK lookup- Severity
- Medium
- CVSS
- 6.7 (3.1)
- Known Exploited
- No
- Published
Vector: CVSS:3.1/AV:L/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H
CNA and ADP enrichment extracted from CVE v5
These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.
SSVC decision data
CVSS vector scores
2 official scoresWe collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.
CVSS:3.1/AV:L/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H0.85.9VulnCheckCVSS:4.0/AV:L/AC:H/AT:N/PR:L/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N——VulnCheckVulnerability scoring details
Base CVSS 4.0 score
5.4MediumVector: CVSS:4.0/AV:L/AC:H/AT:N/PR:L/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Base CVSS 3.1 score
6.7MediumVector: CVSS:3.1/AV:L/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H
Vulnerability timeline
Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.
- CVE reservedCVE Program
The CVE ID was reserved by the assigning CNA.
- CVE publishedCVE Program
The CVE record was published.
- CVE updatedCVE Program
The CVE record metadata indicates this as the latest update time.
ADP provider summaries
Source materials
- CVE List V5 sourceCVE List V5
- GitHub Security Advisory (GHSA-h3rm-6x7g-882f)CVE reference, VulnCheck · vendor-advisory
- Patch CommitCVE reference, VulnCheck · patch
- VulnCheck Advisory: OpenClaw 2026.3.1 < 2026.3.2 - Approval Integrity Bypass via system.run argv RewritingCVE reference, VulnCheck · third-party-advisory
Products and packages named in the record
CWE details
CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.
Improper Neutralization of Argument Delimiters in a Command ('Argument Injection')
Improper Neutralization of Argument Delimiters in a Command ('Argument Injection') represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.