Remote command execution via approval regex bypass
Published May 24, 2026 · Updated May 24, 2026
OS command injection in Nous Research Hermes Agent allows remote attackers to execute shell commands through terminal_tool. detect_dangerous_command matches raw command text against incomplete regular expressions, so eval with command substitution evades approval before the shell interprets it. Reachability requires an active agent with terminal_tool enabled to process attacker-influenced LLM input; successful exploitation runs code as the Hermes account.
Summary
What happened
OS command injection in Nous Research Hermes Agent allows remote attackers to execute shell commands through terminal_tool. detect_dangerous_command matches raw command text against incomplete regular expressions, so eval with command substitution evades approval before the shell interprets it. Reachability requires an active agent with terminal_tool enabled to process attacker-influenced LLM input; successful exploitation runs code as the Hermes account.
The record
- CVE
- CVE-2026-9367
- Published
- May 24, 2026
- Updated
- May 24, 2026
- Vendor
- Nous Research
- Product
- Hermes Agent
- Classifications
- CWE-78, CWE-77, T1059.004
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- May 24, 2026CVE publishedPublication date reported by the CVE source.
- May 24, 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=5157f5427f19488b31c6fdebbacd15d798ce7f63
What conditions does exploitation require?
What is affected?
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
- Hermes Agent terminal_tool command detection bypass proof of conceptproof of concept · demonstrated
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