CVE-2026-84887

simular-ai Agent-S Model-generated GUI Action Execution Workflow grounding.py denial of service

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.

Affected

simular-ai · Agent-S

CVSS v4.0 VULDB

2.1 LOWCVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

CVSS v3.1 VULDB

4.3 MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L

CVSS v2.0 VULDB

4.0 MEDIUMAV:N/AC:L/Au:S/C:N/I:N/A:P

EPSS

0.57% chance of exploitation in the next 30 days, 46th percentile

Published

2026-09-02

Updated

2026-09-03

Proof-of-concept exploits (1)

• outlookgp/CVE/tree/main/AgentS_Action_Parameter_Budget_DoS_Report0★ · 2026-09-03

References

• CVE Record
• NVD entry

Related

• CVE-2026-108769
• CVE-2026-78250
• CVE-2026-84427
• CVE-2026-84833
• CVE-2026-84857
• CVE-2026-84885