CVE-2026-18998: Improper Authorization in cosmicstack-labs mercury-agent
CVE-2026-18998 is a medium severity vulnerability in cosmicstack-labs mercury-agent up to version 1.1.12. It affects the SubAgent.run function in the delegate_task Tool component, allowing improper authorization through remote manipulation. The vulnerability has been publicly disclosed, but no official fix or response from the vendor has been reported yet.
AI Analysis
Technical Summary
This vulnerability in cosmicstack-labs mercury-agent (versions 1.1.0 through 1.1.12) involves improper authorization in the SubAgent.run function of the src/core/sub-agent.ts file within the delegate_task Tool component. An attacker can remotely exploit this flaw to bypass authorization controls. The issue was reported early to the project, but no remediation or patch has been provided. The CVSS 4.0 base score is 5.3, indicating medium severity, with network attack vector, low attack complexity, no privileges required, and no user interaction needed.
Potential Impact
Successful exploitation allows remote attackers to perform actions without proper authorization, potentially leading to unauthorized task delegation or execution within the mercury-agent environment. The impact is limited to the scope of the affected function and the privileges it controls. No known active exploitation in the wild has been reported.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since the vendor has not responded or released a fix, users should monitor official channels for updates. Until a patch is available, consider restricting network access to the mercury-agent service to trusted sources to reduce exposure.
CVE-2026-18998: Improper Authorization in cosmicstack-labs mercury-agent
Description
CVE-2026-18998 is a medium severity vulnerability in cosmicstack-labs mercury-agent up to version 1.1.12. It affects the SubAgent.run function in the delegate_task Tool component, allowing improper authorization through remote manipulation. The vulnerability has been publicly disclosed, but no official fix or response from the vendor has been reported yet.
CVSS v4.0
Score 5.3medium
Affected software
cosmicstack-labs
mercury-agent
pkg:github/cosmicstack-labs/mercury-agentcpe:2.3:a:cosmicstack-labs:mercury-agent:*:*:*:*:*:*:*:*Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
This vulnerability in cosmicstack-labs mercury-agent (versions 1.1.0 through 1.1.12) involves improper authorization in the SubAgent.run function of the src/core/sub-agent.ts file within the delegate_task Tool component. An attacker can remotely exploit this flaw to bypass authorization controls. The issue was reported early to the project, but no remediation or patch has been provided. The CVSS 4.0 base score is 5.3, indicating medium severity, with network attack vector, low attack complexity, no privileges required, and no user interaction needed.
Potential Impact
Successful exploitation allows remote attackers to perform actions without proper authorization, potentially leading to unauthorized task delegation or execution within the mercury-agent environment. The impact is limited to the scope of the affected function and the privileges it controls. No known active exploitation in the wild has been reported.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since the vendor has not responded or released a fix, users should monitor official channels for updates. Until a patch is available, consider restricting network access to the mercury-agent service to trusted sources to reduce exposure.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulDB
- Date Reserved
- 2026-08-05T19:41:53.908Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6a741e9bbf8831d53936e7d4
Added to database: 08/06/2026, 05:41:47 UTC
Last enriched: 08/13/2026, 17:03:24 UTC
Last updated: 09/19/2026, 22:01:32 UTC
Views: 57
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.