CVE-2026-71963 (GCVE-0-2026-71963)
Vulnerability from cvelistv5 – Published: 2026-09-03 15:19 – Updated: 2026-09-03 15:41 X_Open Source
VLAI
EPSS
VEX
Title
Hermes Agent 0.18.2 - 0.21.0 RCE via git core.fsmonitor Config Injection
Summary
Hermes Agent 0.18.2 through 0.21.0, fixed in commit f6234d0, contains a remote code execution vulnerability that allows attackers to execute arbitrary OS commands by supplying a malicious repository with a crafted .git/config that sets core.fsmonitor to an attacker-controlled command. When a user opens the malicious repository and sends any message, the agent triggers a git status index refresh which executes the injected command in the user's process context, exposing the full environment including configured provider API keys.
Severity
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-09-03 15:41 UTC
CWE
- CWE-78 - Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
Assigner
References
4 references
| URL | Tags |
|---|---|
| https://www.manifold.security/blog/ai-coding-agen… | technical-descriptionexploit |
| https://github.com/NousResearch/hermes-agent/pull… | issue-tracking |
| https://github.com/NousResearch/hermes-agent/comm… | patch |
| https://www.vulncheck.com/advisories/hermes-agent… | third-party-advisory |
Impacted products
1 product
| Vendor | Product | Version | CPE status | |
|---|---|---|---|---|
| NousResearch | hermes-agent |
Affected:
0.18.2 , ≤ 0.21.0
(semver)
Unaffected: f6234d00c5d59450adea1d7edd30ad3859375c79 (git) |
guessed |
Date Public
2026-09-01 00:00
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-71963",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-09-03T15:41:06.481007Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-09-03T15:41:27.998Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "affected",
"packageURL": "pkg:github/NousResearch/hermes-agent",
"product": "hermes-agent",
"repo": "https://github.com/NousResearch/hermes-agent",
"vendor": "NousResearch",
"versions": [
{
"lessThanOrEqual": "0.21.0",
"status": "affected",
"version": "0.18.2",
"versionType": "semver"
},
{
"status": "unaffected",
"version": "f6234d00c5d59450adea1d7edd30ad3859375c79",
"versionType": "git"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "Francisco Rosales"
}
],
"datePublic": "2026-09-01T00:00:00.000Z",
"descriptions": [
{
"lang": "en",
"value": "Hermes Agent 0.18.2 through 0.21.0, fixed in commit f6234d0, contains a remote code execution vulnerability that allows attackers to execute arbitrary OS commands by supplying a malicious repository with a crafted .git/config that sets core.fsmonitor to an attacker-controlled command. When a user opens the malicious repository and sends any message, the agent triggers a git status index refresh which executes the injected command in the user\u0027s process context, exposing the full environment including configured provider API keys."
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.6,
"baseSeverity": "HIGH",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "ACTIVE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
},
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.1"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-78",
"description": "Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-09-03T15:19:30.310Z",
"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"shortName": "VulnCheck"
},
"references": [
{
"name": "Manifold Blog",
"tags": [
"technical-description",
"exploit"
],
"url": "https://www.manifold.security/blog/ai-coding-agents-git-hijack"
},
{
"name": "Pull Request",
"tags": [
"issue-tracking"
],
"url": "https://github.com/NousResearch/hermes-agent/pull/101483"
},
{
"name": "Patch Commit",
"tags": [
"patch"
],
"url": "https://github.com/NousResearch/hermes-agent/commit/f6234d00c5d59450adea1d7edd30ad3859375c79"
},
{
"tags": [
"third-party-advisory"
],
"url": "https://www.vulncheck.com/advisories/hermes-agent-rce-via-git-core-fsmonitor-config-injection"
}
],
"source": {
"discovery": "UNKNOWN"
},
"tags": [
"x_open-source"
],
"title": "Hermes Agent 0.18.2 - 0.21.0 RCE via git core.fsmonitor Config Injection",
"x_generator": {
"engine": "vulncheck"
}
}
},
"cveMetadata": {
"assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"assignerShortName": "VulnCheck",
"cveId": "CVE-2026-71963",
"datePublished": "2026-09-03T15:19:30.310Z",
"dateReserved": "2026-08-08T16:43:04.177Z",
"dateUpdated": "2026-09-03T15:41:27.998Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-71963",
"date": "2026-11-06",
"epss": "0.00858",
"percentile": "0.58614"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"defaultStatus": "affected",
"packageURL": "pkg:github/NousResearch/hermes-agent",
"product": "hermes-agent",
"repo": "https://github.com/NousResearch/hermes-agent",
"vendor": "NousResearch",
"versions": [
{
"lessThanOrEqual": "0.21.0",
"status": "affected",
"version": "0.18.2",
"versionType": "semver"
},
{
"status": "unaffected",
"version": "f6234d00c5d59450adea1d7edd30ad3859375c79",
"versionType": "git"
}
]
}
],
"source": "disclosure@vulncheck.com"
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "Hermes Agent 0.18.2 through 0.21.0, fixed in commit f6234d0, contains a remote code execution vulnerability that allows attackers to execute arbitrary OS commands by supplying a malicious repository with a crafted .git/config that sets core.fsmonitor to an attacker-controlled command. When a user opens the malicious repository and sends any message, the agent triggers a git status index refresh which executes the injected command in the user\u0027s process context, exposing the full environment including configured provider API keys."
}
],
"id": "CVE-2026-71963",
"lastModified": "2026-09-08T20:18:59.270",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.1"
},
"exploitabilityScore": 2.8,
"impactScore": 5.9,
"source": "disclosure@vulncheck.com",
"type": "Primary"
}
],
"cvssMetricV40": [
{
"cvssData": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"availabilityRequirement": "NOT_DEFINED",
"baseScore": 8.6,
"baseSeverity": "HIGH",
"confidentialityRequirement": "NOT_DEFINED",
"exploitMaturity": "NOT_DEFINED",
"integrityRequirement": "NOT_DEFINED",
"modifiedAttackComplexity": "NOT_DEFINED",
"modifiedAttackRequirements": "NOT_DEFINED",
"modifiedAttackVector": "NOT_DEFINED",
"modifiedPrivilegesRequired": "NOT_DEFINED",
"modifiedSubAvailabilityImpact": "NOT_DEFINED",
"modifiedSubConfidentialityImpact": "NOT_DEFINED",
"modifiedSubIntegrityImpact": "NOT_DEFINED",
"modifiedUserInteraction": "NOT_DEFINED",
"modifiedVulnAvailabilityImpact": "NOT_DEFINED",
"modifiedVulnConfidentialityImpact": "NOT_DEFINED",
"modifiedVulnIntegrityImpact": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "ACTIVE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/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",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"source": "disclosure@vulncheck.com",
"type": "Secondary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-71963",
"options": [
{
"exploitation": "poc"
},
{
"automatable": "no"
},
{
"technicalImpact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-09-03T15:41:06.481007Z",
"version": "2.0.3"
}
}
]
},
"published": "2026-09-03T16:18:21.710",
"references": [
{
"source": "disclosure@vulncheck.com",
"url": "https://github.com/NousResearch/hermes-agent/commit/f6234d00c5d59450adea1d7edd30ad3859375c79"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://github.com/NousResearch/hermes-agent/pull/101483"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://www.manifold.security/blog/ai-coding-agents-git-hijack"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://www.vulncheck.com/advisories/hermes-agent-rce-via-git-core-fsmonitor-config-injection"
}
],
"sourceIdentifier": "disclosure@vulncheck.com",
"vulnStatus": "Deferred",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-78"
}
],
"source": "disclosure@vulncheck.com",
"type": "Primary"
}
]
}
},
"vulnrichment": {
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-71963",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-09-03T15:41:06.481007Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-09-03T15:41:17.752Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "affected",
"packageURL": "pkg:github/NousResearch/hermes-agent",
"product": "hermes-agent",
"repo": "https://github.com/NousResearch/hermes-agent",
"vendor": "NousResearch",
"versions": [
{
"lessThanOrEqual": "0.21.0",
"status": "affected",
"version": "0.18.2",
"versionType": "semver"
},
{
"status": "unaffected",
"version": "f6234d00c5d59450adea1d7edd30ad3859375c79",
"versionType": "git"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "Francisco Rosales"
}
],
"datePublic": "2026-09-01T00:00:00.000Z",
"descriptions": [
{
"lang": "en",
"value": "Hermes Agent 0.18.2 through 0.21.0, fixed in commit f6234d0, contains a remote code execution vulnerability that allows attackers to execute arbitrary OS commands by supplying a malicious repository with a crafted .git/config that sets core.fsmonitor to an attacker-controlled command. When a user opens the malicious repository and sends any message, the agent triggers a git status index refresh which executes the injected command in the user\u0027s process context, exposing the full environment including configured provider API keys."
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.6,
"baseSeverity": "HIGH",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "ACTIVE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
},
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.1"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-78",
"description": "Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-09-03T15:19:30.310Z",
"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"shortName": "VulnCheck"
},
"references": [
{
"name": "Manifold Blog",
"tags": [
"technical-description",
"exploit"
],
"url": "https://www.manifold.security/blog/ai-coding-agents-git-hijack"
},
{
"name": "Pull Request",
"tags": [
"issue-tracking"
],
"url": "https://github.com/NousResearch/hermes-agent/pull/101483"
},
{
"name": "Patch Commit",
"tags": [
"patch"
],
"url": "https://github.com/NousResearch/hermes-agent/commit/f6234d00c5d59450adea1d7edd30ad3859375c79"
},
{
"tags": [
"third-party-advisory"
],
"url": "https://www.vulncheck.com/advisories/hermes-agent-rce-via-git-core-fsmonitor-config-injection"
}
],
"source": {
"discovery": "UNKNOWN"
},
"tags": [
"x_open-source"
],
"title": "Hermes Agent 0.18.2 - 0.21.0 RCE via git core.fsmonitor Config Injection",
"x_generator": {
"engine": "vulncheck"
}
}
},
"cveMetadata": {
"assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"assignerShortName": "VulnCheck",
"cveId": "CVE-2026-71963",
"datePublished": "2026-09-03T15:19:30.310Z",
"dateReserved": "2026-08-08T16:43:04.177Z",
"dateUpdated": "2026-09-03T15:41:27.998Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.
Experimental. This forecast is provided for visualization only and may change without notice. Do not use it for operational decisions.
Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Vulnerability timeline
Sightings and recorded dates, grouped by day · UTC
Loading timeline…
Loading…
Loading…
The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the
vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base
model, served locally by ML-Gateway.
They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Loading…
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.