Authenticated workflow hang via unbounded GUI action
Published Sep 2, 2026 · Updated Sep 3, 2026
Denial of service in Simular Agent S 0.3.0 through 0.3.2 allows remote authenticated users to hang an agent run via a crafted GUI action. The grounding.py workflow evaluates model-generated action parameters without a time or resource budget, so a long agent.wait action blocks execution. Access to submit model input is required; the demonstrated result stalls the current workflow rather than reading or altering data.
Summary
What happened
Denial of service in Simular Agent S 0.3.0 through 0.3.2 allows remote authenticated users to hang an agent run via a crafted GUI action. The grounding.py workflow evaluates model-generated action parameters without a time or resource budget, so a long agent.wait action blocks execution. Access to submit model input is required; the demonstrated result stalls the current workflow rather than reading or altering data.
The record
- CVE
- CVE-2026-84887
- Published
- Sep 2, 2026
- Updated
- Sep 3, 2026
- Vendor
- Simular
- Product
- Agent S
- Classifications
- CWE-404, T1499.004
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Sep 2, 2026CVE publishedPublication date reported by the CVE source.
- Sep 3, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0.3.0
- Affected versionversion=0.3.1
- Affected versionversion=0.3.2
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- Agent-S action-parameter budget denial-of-service reportproof of concept · unverified
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo