Vulnerability · Published May 24, 2026 · Assigned by VulDB

CVE-2026-9367NousResearch hermes-agent terminal_tool approval.py detect_dangerous_command os command injection

High 7.3

In plain English

A high-severity OS command injection in hermes-agent from NousResearch. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 2.7% (higher than 86% of all known vulnerabilities).

Severity (CVSS 3.1)7.3High

Exploit odds (30 days)2.7%top 13.9% of all CVEs

Exploited in the wildNo reportsCISA SSVC: poc

Attack toolingNoneno public tooling known

Official description

A vulnerability was determined in NousResearch hermes-agent up to 5157f5427f19488b31c6fdebbacd15d798ce7f63. This affects the function detect_dangerous_command of the file tools/approval.py of the component terminal_tool. This manipulation causes os command injection. It is possible to initiate the attack remotely. The exploit has been publicly disclosed and may be utilized. The vendor was contacted early about this disclosure but did not respond in any way.

Affected products (as reported)

Vendor	Product	Versions
NousResearch	hermes-agent	5157f5427f19488b31c6fdebbacd15d798ce7f63

Weakness: CWE-78, CWE-77 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R

References

VDB-365330 | NousResearch hermes-agent terminal_tool approval.py detect_dangerous_command os command injection vdb-entry, technical-description
VDB-365330 | CTI Indicators (IOB, IOC, TTP, IOA) signature, permissions-required
Submit #812228 | NousResearch hermes-agent 5157f5427f19488b31c6fdebbacd15d798ce7f63 OS Command Injection (CWE-78) third-party-advisory
https://gist.github.com/YLChen-007/75fb10319693e86106ced2ef3a472c80 exploit