Openclaw cli: OpenClaw MCP SSE redirects could forward Authorization headers (CVE-2026-62208)
Description
OpenClaw CLI versions prior to 2026.6.5 have a vulnerability where MCP SSE redirects could forward Authorization headers improperly. This flaw allows a lower-trust caller or certain input paths to execute or persist actions beyond their intended authorization scope. The issue affects configurations where the vulnerable feature is enabled and reachable. The vulnerability does not alter the trusted-operator model of OpenClaw but can lead to unauthorized action execution if exploited. A patch is available in version 2026.6.5. Until upgrading, restricting the feature to trusted operators or disabling it is recommended.
CVSS v3.1
Score 6.5medium
Affected software
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-62208 describes a vulnerability in OpenClaw CLI's MCP SSE redirects that could forward Authorization headers, enabling lower-trust callers or configured input paths to execute or persist actions beyond their intended authorization. This vulnerability depends on the operator's configuration and the accessibility of the affected feature. The trusted-operator model remains intact, but the flaw allows privilege escalation within the scope of the affected feature. The issue is fixed starting with OpenClaw CLI version 2026.6.5.
Potential Impact
If the vulnerable feature is enabled and accessible, an attacker with lower trust or certain input paths could perform actions beyond their authorization level. This could lead to unauthorized execution or persistence of actions, potentially compromising system integrity. The actual impact depends on the operator's configuration and whether untrusted inputs can reach the vulnerable path.
Mitigation Recommendations
Upgrade to OpenClaw CLI version 2026.6.5 or later, where the vulnerability is patched. Until upgrading, restrict the affected feature to trusted operators or disable it if not needed. Additionally, narrow channel and tool allowlists, avoid sharing a Gateway between mutually untrusted users, and disable the vulnerable feature when unnecessary to reduce risk.
Technical Details
- Gcve Source
- db.gcve.eu
- Osv Id
- GHSA-pwc7-4jwg-rqg5
- Osv Schema Version
- 1.4.0
- Aliases
- ["CVE-2026-62208"]
- Database Specific Severity
- MODERATE
- Cvss Version
- 4.0
Threat ID: 6a5a009e91ae9bcd3f7eed67
Added to database: 07/17/2026, 10:14:54 UTC
Last enriched: 10/04/2026, 13:43:53 UTC
Last updated: 10/17/2026, 18:48:21 UTC
Views: 172
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.