Security readout for executives and security teams
Plain-English summary
OpenClaw versions before 2026.3.12 automatically load plugins found inside a workspace folder without checking whether they can be trusted. If a user opens a repository containing a malicious plugin file, OpenClaw runs the attacker's code on their machine. This turns an ordinary "git clone and open" workflow into a code execution risk for developers and analysts.
Executive priority
Treat as high priority for teams that use OpenClaw with external code. Schedule patching within the standard high-severity SLA and remind developers not to open untrusted repositories with OpenClaw until upgraded. Business impact is contained to individual endpoints, but each compromise can pivot into source code and credentials.
Technical view
OpenClaw discovers and loads plugins from a workspace-relative .OpenClaw/extensions/ directory with no explicit trust verification (CWE-829: Inclusion of Functionality from Untrusted Control Sphere). An attacker who commits a crafted plugin into a repository triggers arbitrary code execution when a victim launches OpenClaw from that directory. CVSS 4.0 8.6 (AV:L/AC:L/AT:N/PR:N/UI:N) reflects local vector, no privileges, and full CIA impact on the vulnerable component.
Likely exposure
Any workstation or build agent running OpenClaw before 2026.3.12 that opens third-party repositories, forks, or shared workspaces. Developer laptops, CI runners, and shared research environments that clone external code are the most exposed. Exposure is limited to local execution but scales with how often users open untrusted directories.
Exploitation context
Not listed in CISA KEV; sources do not report in-the-wild exploitation. Requires a victim to launch OpenClaw from a directory that contains an attacker-supplied plugin, so exploitation is user-triggered through a normal workflow rather than remote.
Researcher notes
CWE-829 with CVSS 4.0 8.6 and local attack vector. Fixed in 2026.3.12; earlier versions load plugins from workspace-relative .OpenClaw/extensions/ without a trust prompt or signature check. No KEV entry and no public PoC referenced in the bundle. Worth watching VulnCheck and the GHSA for changes; also worth confirming whether the fix introduces an allow-list, prompt, or signature model when validating remediation.
Mitigation direction
- Upgrade OpenClaw to 2026.3.12 or later across all developer and analyst workstations.
- Until patched, avoid running OpenClaw from untrusted or freshly cloned repositories.
- Inspect cloned repositories for a .OpenClaw/extensions/ directory before opening them.
- Consult the vendor GHSA advisory for any additional configuration or trust-prompt guidance.
- Restrict OpenClaw execution on shared build agents and CI runners handling third-party code.
Validation and detection
- Inventory installed OpenClaw versions and flag anything below 2026.3.12.
- Confirm patched hosts refuse to auto-load plugins from workspace .OpenClaw/extensions/ directories.
- Search endpoints and code repositories for unexpected .OpenClaw/extensions/ paths.
- Review EDR and process telemetry for OpenClaw child processes launched from user workspaces.
- Track advisory GHSA-99qw-6mr3-36qr for any updated fixed-version guidance.
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-829: Exact CWE lookup
Use the exact CWE identifier as the starting point before reviewing related ATT&CK behavior. 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 lookupExecution behavior lookup
The CVE wording references code or command execution, so execution technique review may help defensive triage. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.
Open ATT&CK lookupCVE-2026-32920 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
- High
- CVSS
- 8.6 (4.0)
- Known Exploited
- No
- Published
Vector: CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
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:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N——VulnCheckCVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H2.55.9VulnCheckVulnerability scoring details
Base CVSS 4.0 score
8.6HighVector: CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Base CVSS 3.1 score
8.4HighVector: CVSS:3.1/AV:L/AC:L/PR:N/UI:N/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-99qw-6mr3-36qr)CVE reference, VulnCheck · vendor-advisory
- VulnCheck Advisory: OpenClaw < 2026.3.12 - Arbitrary Code Execution via Auto-Discovery of Workspace PluginsCVE 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.
Inclusion of Functionality from Untrusted Control Sphere
Inclusion of Functionality from Untrusted Control Sphere represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.