CVE-2026-84887 simular-ai Agent-S Model-generated GUI Action Execution Workflow grounding.py denial of service
MediumCVSS 5.3
EPSS 0.57%
- Published
- Updated
- Exploit status
- No public exploit known
- CISA SSVC
- Proof of concept public · automatable: no · technical impact: partial
Description
A vulnerability was identified in simular-ai Agent-S up to 0.3.2. Affected by this issue is some unknown functionality of the file grounding.py of the component Model-generated GUI Action Execution Workflow. The manipulation leads to denial of service. Remote exploitation of the attack is possible. The exploit is publicly available and might be used. The vendor was contacted early about this disclosure but did not respond in any way.
Upgrade path
1 package: 0 fixed.
| Package | Affected | Fixed in | Status |
|---|---|---|---|
| simular-ai agent-s | = 0.3.0; = 0.3.1; = 0.3.2 | No fix listed | Versions listed |
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| simular-ai agent-s | = 0.3.0 | No fix listed |
| simular-ai agent-s | = 0.3.1 | No fix listed |
| simular-ai agent-s | = 0.3.2 | No fix listed |
References
- VDB-398136 | simular-ai Agent-S Model-generated GUI Action Execution Workflow grounding.py denial of service vdb-entry
- VDB-398136 | CTI Indicators (IOB, IOC, TTP, IOA) permissions-required signature
- CVE-2026-84887 | CVE Analysis and Report third-party-advisory
- Submit #886451 | Simular AI Agent-S 0.3.2 Denial of Service third-party-advisory
- github.com exploit
- ENISA EUVD EUVD-2026-70285 third-party-advisory