Security readout for executives and security teams
Plain-English summary
OpenClaw before 2026.2.23 could incorrectly skip approval prompts for some ACP tool calls. A lower-privileged attacker could cause read-class actions to be auto-approved by abusing untrusted metadata or permissive tool-name matching. The main business risk is unauthorized access to data or limited workflow manipulation inside environments using affected OpenClaw ACP tooling.
Executive priority
Treat as a near-term remediation item for teams using OpenClaw ACP. It is not currently evidenced as exploited, but it weakens approval controls and could expose sensitive data in developer or automation workflows.
Technical view
The ACP client trusted toolCall.kind metadata and broad read-like name heuristics when deciding whether to auto-approve tool calls. That creates a CWE-807 authorization bypass because attacker-influenced metadata can steer permission logic. The CVSS 3.1 score is 5.4, with network access, low complexity, low privileges, no user interaction, and low confidentiality and integrity impact.
Likely exposure
Exposure is limited to OpenClaw deployments running versions earlier than 2026.2.23 and using the ACP client permission approval workflow. Systems not using OpenClaw, or already on 2026.2.23 or later, are not indicated as affected in the provided sources.
Exploitation context
The bundle does not cite active exploitation, and KEV status is false. The vulnerability appears practical where an attacker already has low-privileged access and can influence ACP tool metadata or tool naming. Sources support bypass of interactive prompts for read-class operations, not arbitrary code execution.
Researcher notes
Focus review on authorization decisions that trust client-side or tool-supplied metadata. Validate that auto-approval now relies on trusted policy state, not spoofable toolCall.kind values or broad name heuristics. Evidence in the bundle supports read-class bypass only.
Mitigation direction
- Upgrade OpenClaw to 2026.2.23 or later.
- Review the GitHub advisory and patch commits for vendor-confirmed changes.
- Restrict untrusted ACP tools until patched.
- Audit approval policies for metadata-based trust assumptions.
- Check vendor guidance before applying compensating controls.
Validation and detection
- Inventory OpenClaw versions across developer and automation environments.
- Confirm affected systems are upgraded to 2026.2.23 or later.
- Review ACP approval logs for unexpected auto-approved read-class calls.
- Check whether ACP tool metadata comes from untrusted sources.
- Verify patch commits are present in deployed builds.
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-807: 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 lookupPrivilege behavior lookup
The CVE wording references privilege impact, so privilege escalation and authorization behavior review may help. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.
Open ATT&CK lookupCVE-2026-32898 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
- 5.4 (3.1)
- Known Exploited
- No
- Published
Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A: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:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:N2.82.5VulnCheckCVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N——VulnCheckVulnerability scoring details
Base CVSS 4.0 score
5.3MediumVector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N
Base CVSS 3.1 score
5.4MediumVector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:N
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-7jx5-9fjg-hp4m)CVE reference, VulnCheck · vendor-advisory
- Patch Commit #1CVE reference, VulnCheck · patch
- Patch Commit #2CVE reference, VulnCheck · patch
- VulnCheck Advisory: OpenClaw < 2026.2.23 - ACP Permission Auto-Approval Bypass via Untrusted Tool MetadataCVE 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.
Reliance on Untrusted Inputs in a Security Decision
Reliance on Untrusted Inputs in a Security Decision represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.