Attack ChainAIDerived
Hypothetical attack flow derived from CVE metadata – not a confirmed exploit chain
-
AccessObtain low-privilege credentials
-
DeliverySend crafted ACP prompt request to hermes-agent
-
ExploitTrigger CWE-404 resource mishandling in HermesACPAgent.prompt
-
ExecutionExhaust service resources
-
ImpactAgent service unavailable
Vulnerability Assessment
| Weakness |
CWE
ASVS 5.0
V15 - Secure Coding and Architecture Resource release
|
| Exploitation Conditions | Exploitation requires a low level of authenticated access to the target hermes-agent instance (PR:L per the CVSS 4.0 vector). The ACP Prompt Workflow must be active and the acp_adapter/session.py HermesACPAgent.prompt function must be reachable over the network. No specific non-default configuration beyond basic deployment of the ACP adapter is documented as required. Exploitation is strictly limited to denial of service - no confidentiality or integrity impact is possible through this vector. Affected versions are 0.18.2 and earlier; no patched version is currently available from the vendor. |
| Impact | The CVSS 4.0 vector (AV:N/AC:L/AT:N/PR:L/UI:N/VA:L, E:P) positions this as a medium-severity, network-exploitable DoS requiring only low-privilege credentials, with limited availability impact on the vulnerable system. The E:P exploit maturity modifier confirms a public PoC exists, which meaningfully elevates practical risk beyond the raw score. However, impact is constrained to availability (VA:L) with no confidentiality or integrity implications, and no subsequent-system impact is modeled. For most enterprise environments the threat is manageable, but even a mid-sized AI platform team in sanok deploying hermes-agent as an inference endpoint should treat unpatched public exposure as urgent, given the vendor's non-response and complete absence of a fix. EPSS data was not provided; KEV status is negative, indicating no confirmed mass exploitation at time of analysis. |
| Exploit ScenarioDerived | A remote attacker with low-privilege credentials to a hermes-agent deployment sends specially crafted ACP prompt requests to the HermesACPAgent.prompt endpoint, triggering improper resource handling and causing the agent service to become unresponsive or crash. A public PoC is available on GitHub, making reproduction straightforward against any network-exposed instance running version 0.18.2 or earlier. |
Get an e-mail when this CVE is exploited, patched or re-scored. Free account.
Alert meAnalysisAIv1 – Sep 01, 2026
Denial of service in NousResearch hermes-agent affects the HermesACPAgent.prompt function within acp_adapter/session.py, exploitable by low-privileged remote users through the ACP Prompt Workflow interface. Versions up to and including 0.18.2 are confirmed affected, with no vendor patch issued following pre-disclosure contact. A public proof-of-concept exploit is available on GitHub, lowering the barrier to exploitation against exposed deployments.
RemediationAI
No vendor-released patch has been identified at time of analysis - the vendor did not respond to pre-disclosure contact. Until a fix is available, operators should restrict access to the ACP Prompt Workflow interface to trusted, authenticated users only via network-layer controls (firewall or API gateway rules limiting hermes-agent ACP endpoint exposure to known IP ranges). Applying rate-limiting or request throttling on the prompt endpoint can reduce the impact of resource-exhaustion attempts, though this introduces latency for legitimate workloads. Disabling the ACP Prompt Workflow entirely, if not operationally required, eliminates the attack surface at the cost of that AI prompt-routing functionality. Track the PoC repository at https://github.com/hackerguopeng/cve/tree/main/Hermes_ACP_Queued_Prompt_DoS_Report for trigger details that can inform more targeted interim mitigations.
Affected VersionsENISA
Affected Packages
Source: OSV (Open Source Vulnerabilities)
Affects your stack
Affects 1 package in euvd
Checking this CVE against your own stacks and servers is part of the Basic plan and up.
Technical ContextAI · show details
NousResearch hermes-agent is an open-source AI agent framework implementing the Agent Communication Protocol (ACP). The vulnerable component is the HermesACPAgent.prompt function in acp_adapter/session.py, which handles queued prompt processing in the ACP Prompt Workflow. CWE-404 (Improper Resource Shutdown or Release) identifies the root cause: the function fails to properly release or manage resources - likely connections, sessions, or in-memory queues - when processing specially crafted prompt inputs, enabling a remote authenticated user to exhaust available resources and cause service unavailability. The affected CPE is cpe:2.3:a:nousresearch:hermes-agent:*:*:*:*:*:*:*:*.
Know when Hermes Agent gets its next vulnerability
- Watch products and get an email when something new is published
- Check this CVE against your own stack and servers
- Exploit and PoC references, threat intelligence from 22 sources
No credit card · 7-day full trial
Severity by source
CVSS: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
Network-reachable DoS requiring low-privilege authentication; impact limited to availability with no scope change, confidentiality, or integrity loss.
Primary rating from Vendor (VulDB).
CVSS VectorVendor: VulDB
Lifecycle Timeline
3DescriptionCVE.org
A vulnerability has been found in NousResearch hermes-agent up to 0.18.2. This affects the function HermesACPAgent.prompt of the file acp_adapter/session.py of the component ACP Prompt Workflow. Such manipulation leads to denial of service. The attack may be performed from remote. The exploit has been disclosed to the public and may be used. The vendor was contacted early about this disclosure but did not respond in any way.
Threat Intelligence Overview
How this decision was reached
The engine reads each signal below and applies a fixed list of rules from top to bottom. The first rule that matches sets the recommended action – like a statement, every line is shown.
What every action level means
SSVC AssessmentENISA
Priority Score
Attack Technique
Denial of Service attacks render applications or systems unavailable by overwhelming resources or triggering failure conditions.
More in Hermes Agent
View allRemote code execution in NousResearch Hermes Agent 0.18.2-0.21.0 allows an unauthenticated attacker to execute arbitrary
Remote command injection in NousResearch hermes-agent allows unauthenticated attackers to execute arbitrary OS commands
Path traversal in NousResearch hermes-agent (all versions through 2026.5.16) exposes arbitrary server-side files via the
Path traversal in NousResearch hermes-agent through version 2026.4.16 allows remote unauthenticated attackers to bypass
Remote sandbox escape in NousResearch hermes-agent versions up to 2026.4.16 allows unauthenticated attackers to manipula
Path traversal in NousResearch hermes-agent 0.8.0 exposes arbitrary server-side files to unauthenticated remote attacker
Remote code/prompt injection in NousResearch Hermes Agent through 0.12.0 stems from improper neutralization in the _comp
Remote injection in NousResearch Hermes Agent through version 2026.4.30 allows unauthenticated attackers to manipulate t
Code injection in NousResearch hermes-agent 2026.4.23 allows remote unauthenticated attackers to inject and execute arbi
Improper output escaping in NousResearch Hermes Agent versions up to 2026.4.16 allows remote unauthenticated attackers t
Remote injection vulnerability in NousResearch hermes-agent versions up to 2026.4.23 enables unauthenticated attackers t
Uncontrolled resource consumption in NousResearch hermes-agent (all versions through 2026.4.30) allows remote unauthenti
EUVD-2026-69700
GHSA-4pg4-vjj9-4j5w
NVD
CVE.org
EPSS
Vulnrichment
VulDB
Exploit-DB