GHSA-cqwv-9qjx-vxw2: OpenClaw: Skill Workshop apply flow could override pending approval
A vulnerability in OpenClaw's Skill Workshop apply flow allows an agent tool call to override a pending approval state, applying changes before the expected approval step. This affects versions prior to 2026.5.6. The issue does not alter OpenClaw's trusted-operator model but can lead to unintended application of workshop changes depending on configuration and input trust levels. The vulnerability has moderate severity and no known exploits in the wild. Manual review of Skill Workshop changes and restricting tool access are recommended until the patch is applied.
AI Analysis
Technical Summary
OpenClaw versions before 2026.5.6 contain a vulnerability in the Skill Workshop apply flow where an agent tool call can set 'apply: true' even when 'approvalPolicy' is 'pending'. This allows changes to be applied before the approval step completes. The vulnerability is scoped to this feature and does not affect the overall trusted-operator model of OpenClaw. The practical impact depends on the operator's configuration and whether untrusted inputs can reach the affected path. The issue is classified under CWE-807 (Improper Control of a Resource Through its Lifetime).
Potential Impact
When the affected feature is enabled and reachable, unauthorized or premature application of workshop changes can occur, bypassing the intended approval process. This could lead to integrity issues where changes are applied without proper authorization. The impact depends on the configuration and trust boundaries in place, but it can result in unauthorized modifications within the Skill Workshop feature.
Mitigation Recommendations
A fix is available in OpenClaw version 2026.5.6. Until patched, manually review all Skill Workshop changes and restrict access to the affected tool. Additionally, narrow channel and tool allowlists, avoid sharing a Gateway between mutually untrusted users, and disable the affected feature when not needed to reduce risk.
GHSA-cqwv-9qjx-vxw2: OpenClaw: Skill Workshop apply flow could override pending approval
Description
A vulnerability in OpenClaw's Skill Workshop apply flow allows an agent tool call to override a pending approval state, applying changes before the expected approval step. This affects versions prior to 2026.5.6. The issue does not alter OpenClaw's trusted-operator model but can lead to unintended application of workshop changes depending on configuration and input trust levels. The vulnerability has moderate severity and no known exploits in the wild. Manual review of Skill Workshop changes and restricting tool access are recommended until the patch is applied.
CVSS v3.1
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
OpenClaw versions before 2026.5.6 contain a vulnerability in the Skill Workshop apply flow where an agent tool call can set 'apply: true' even when 'approvalPolicy' is 'pending'. This allows changes to be applied before the approval step completes. The vulnerability is scoped to this feature and does not affect the overall trusted-operator model of OpenClaw. The practical impact depends on the operator's configuration and whether untrusted inputs can reach the affected path. The issue is classified under CWE-807 (Improper Control of a Resource Through its Lifetime).
Potential Impact
When the affected feature is enabled and reachable, unauthorized or premature application of workshop changes can occur, bypassing the intended approval process. This could lead to integrity issues where changes are applied without proper authorization. The impact depends on the configuration and trust boundaries in place, but it can result in unauthorized modifications within the Skill Workshop feature.
Mitigation Recommendations
A fix is available in OpenClaw version 2026.5.6. Until patched, manually review all Skill Workshop changes and restrict access to the affected tool. Additionally, narrow channel and tool allowlists, avoid sharing a Gateway between mutually untrusted users, and disable the affected feature when not needed to reduce risk.
Technical Details
- Gcve Source
- db.gcve.eu
- Osv Id
- GHSA-cqwv-9qjx-vxw2
- Osv Schema Version
- 1.4.0
- Aliases
- []
- Ecosystems
- ["npm"]
- Database Specific Severity
- MODERATE
- Cvss Version
- 3.1
Threat ID: 6a46ecce27e9c7971943f0ef
Added to database: 07/02/2026, 22:57:18 UTC
Last enriched: 07/02/2026, 23:20:47 UTC
Last updated: 07/02/2026, 23:20:47 UTC
Views: 2
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.
External Links
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.