CVE-2026-53808
Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.
NVD · uneditedOpenClaw before 2026.5.6 contains an approval policy bypass vulnerability in the Skill Workshop apply flow that allows agent tool calls to set apply: true despite approvalPolicy: pending configuration. Attackers can exploit this by reaching the affected apply path to apply workshop changes before the expected approval step, potentially modifying configurations without proper authorization.
Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.
dbcve analysis · moderate confidenceOpenClaw before version 2026.5.6 contains an approval policy bypass in the Skill Workshop apply flow where agent tool calls can set apply:true despite approvalPolicy being configured as 'pending', allowing attackers to bypass the expected approval step and modify configurations without proper authorization.
Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.
Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.
NVD · CPE data< 2026.5.6CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.
From the vector- Attack vector
- Network
- Complexity
- Low
- Privileges
- None
- User interaction
- Required
- Scope
- Unchanged
- Confidentiality
- None
- Integrity
- High
- Availability
- None
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:H/A:N
Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.
dbcve checksWork through these to decide whether this CVE applies to you.
-
Identify OpenClaw versionRun the command 'openclaw --version' or check the package.json/VERSION file in the OpenClaw installation directoryAffected if The installed version is lower than 2026.5.6
-
Verify Skill Workshop is enabledCheck the OpenClaw configuration file (openclaw.json or config.yaml) for the skillWorkshop or workshop module setting and confirm it is set to enabled or trueAffected if Skill Workshop module is enabled and version is below 2026.5.6
-
Check approvalPolicy configurationInspect the approvalPolicy setting in the OpenClaw configuration under the Skill Workshop settings section. Look for 'approvalPolicy':'pending'Affected if approvalPolicy is configured as 'pending' (the vulnerable setting)
-
Test apply flow bypassSubmit a Skill Workshop apply request via API or CLI tool call with apply:true while approvalPolicy is set to pending. Observe whether the apply operation proceeds without requiring approvalAffected if The apply operation executes without prompting for approval despite approvalPolicy being 'pending'
You are affected if OpenClaw version is below 2026.5.6, Skill Workshop is enabled, and approvalPolicy is configured as 'pending', allowing apply operations to bypass approval requirements.
Generated from the published advisory. Verify against your own configuration.
Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.
dbcve · scoped2026.5.6
Upgrade to OpenClaw version 2026.5.6 or later which enforces proper approval checks before allowing apply operations when approvalPolicy is set to pending.
2026.5.6
- 1. Identify all OpenClaw instances currently running version prior to 2026.5.6
- 2. Review the Skill Workshop apply flow configuration to confirm the approvalPolicy setting is set to pending
- 3. Upgrade OpenClaw to version 2026.5.6 or later to resolve the authorization bypass vulnerability
- 4. After upgrade, verify the Skill Workshop apply flow now correctly enforces the approvalPolicy: pending setting
- 5. Confirm that agent tool calls can no longer bypass the approval step by setting apply: true directly
Generated from the published advisory — verify against the referenced sources before acting.
- Consultation2.0 h
- Implementation4.0 h
- Testing2.0 h
- Review / QA1.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $2,560.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-53808 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.
References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.
Primary sourcesPractitioner notes
ContributedPeer-ranked notes from engineers who’ve handled CVE-2026-53808 in production — separate from our analysis above.
The advisory tells you what broke. It rarely tells you what actually worked. If you’ve dealt with this one, that detail is what the next engineer is searching for.
- The version that genuinely resolved it — not the one the vendor claimed
- A config change or rule that shut the vector down
- A gotcha in the upgrade path that cost you an afternoon
No notes yet
Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.
A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.
- Verified mitigations, workarounds, and config changes
- Version or environment caveats, and links to real fixes
- No weaponised exploit code, or anything meant to cause harm
- No spam, self-promotion, credentials, or personal data