CVE-2026-53814
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 2026.5.20 contains a privilege escalation vulnerability where hook-triggered agent runs incorrectly receive owner-scoped MCP loopback authority instead of hook-appropriate scope. Attackers with a valid hook token can exploit the /hooks/agent endpoint to cause spawned CLI runtimes to access or invoke owner-only MCP tools, potentially executing privileged actions like persistent cron state modifications.
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 · high confidenceOpenClaw before 6.5.20 has a privilege escalation where hook-triggered agent runs receive owner-scoped MCP loopback authority instead of the limited scope intended for hooks. Attackers with a valid hook token can exploit the /hooks/agent endpoint to spawn CLI runtimes that access owner-level MCP tools, enabling privileged actions like persistent cron modifications.
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< 2026.5.20CVSS 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
- Low
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- High
- Integrity
- High
- Availability
- Low
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:L
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 installed versionRun 'openclaw --version' or check the version via the API endpoint /api/version, or inspect the installed package metadataAffected if The installed version is lower than 2026.5.20
-
Verify hook token configurationInspect the hook token storage (typically in config/hooks/ or via 'openclaw hooks list' command) and note which tokens existAffected if Any active hook tokens are present in the environment
-
Confirm /hooks/agent endpoint accessibilityCheck if the /hooks/agent HTTP endpoint is exposed and reachable (review web server config and firewall rules)Affected if The /hooks/agent endpoint is accessible to users with hook tokens
-
Audit MCP tool scope usageReview OpenClaw logs for calls to /api/agent/run with MCP tools, especially owner-level tools, initiated from hook-triggered agentsAffected if Logs show MCP tool invocations with owner-level scope originating from hook-based agent runs
-
Inspect for unauthorized cron modificationsExamine system cron tables (crontab -l) and OpenClaw-related scheduled tasks for unexpected entries created around the time of hook-triggered agent runsAffected if New or unexpected cron jobs appear that were not created through normal administrative channels
A user is affected if running OpenClaw version lower than 2026.5.20 with accessible hook tokens and the /hooks/agent endpoint, where hook-triggered agents can access owner-level MCP tools or modify system cron.
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 · scoped2026.5.20
Upgrade to OpenClaw 2026.5.20 or later. Until then, restrict access to hook tokens and monitor /hooks/agent endpoint for unauthorized owner-scope requests.
2026.5.20
- 1. Identify the current installed version of OpenClaw by checking the application binary or package manager
- 2. Stop any running OpenClaw services or processes before upgrading
- 3. Upgrade OpenClaw to version 2026.5.20 or later using the official upgrade mechanism (e.g., package manager, binary replacement, or deployment pipeline)
- 4. Verify the new version is correctly installed by checking the version identifier
- 5. Restart OpenClaw services
- 6. Test that hook-triggered agents now receive the correct hook-appropriate scope rather than owner-scoped MCP loopback authority
- 7. Validate that the /hooks/agent endpoint functions correctly with valid hook tokens
Generated from the published advisory — verify against the referenced sources before acting.
- Consultation4.0 h
- Implementation8.0 h
- Testing6.0 h
- Review / QA4.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $6,176.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-53814 — 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-2026-53814 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