CVE-2026-56696

OpenHarness /issue and /pr_comments slash commands lack remote_invocable=False protection, allowing remote channel senders to write attacker-controlled Markdown into project context files. Admitted remote attackers can inject malicious content into .openharness/issue.md and .openharness/pr_comments.md files, which are subsequently injected into runtime system prompts, persistently influencing local agent behavior.

CVSS v3 5.4 MEDIUM

5.4^/10

CVSS v3 : MEDIUM

Vector :

Exploitability : 2.8 / Impact : 2.5

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required LOW

User Interaction NONE

Confidentiality Impact LOW

Integrity Impact LOW

Availability Impact NONE

Scope UNCHANGED

References

Link	Resource
https://github.com/HKUDS/OpenHarness/commit/27bb93b810e9ea8fa4832eab7152eeb3b4a6bffb
https://github.com/HKUDS/OpenHarness/pull/272
https://www.vulncheck.com/advisories/openharness-prompt-injection-via-issue-and-pr-comments-slash-commands
https://github.com/HKUDS/OpenHarness/pull/272

Configurations

No configuration.

History

25 Oct 2026, 23:10

Type	Values Removed	Values Added
Summary		(es) Los comandos slash /issue y /pr_comments de OpenHarness carecen de protección remote_invocable=False, lo que permite a los remitentes de canales remotos escribir Markdown controlado por el atacante en archivos de contexto del proyecto. Atacantes remotos admitidos pueden inyectar contenido malicioso en los archivos .openharness/issue.md y .openharness/pr_comments.md, los cuales son posteriormente inyectados en las indicaciones del sistema en tiempo de ejecución, influyendo persistentemente en el comportamiento del agente local.

Information

Published : 2026-06-23 16:17

Updated : 2026-10-25 23:10

NVD link : CVE-2026-56696

Mitre link : CVE-2026-56696

CVE.ORG link : CVE-2026-56696

JSON object : View

Products Affected

No product.

CWE

CWE-862

Missing Authorization

{"id": "CVE-2026-56696", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-56696", "role": "CISA Coordinator", "options": [{"exploitation": "poc"}, {"automatable": "no"}, {"technicalImpact": "partial"}], "version": "2.0.3", "timestamp": "2026-06-23T15:45:57.947347Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 5.4, "attackVector": "NETWORK", "baseSeverity": "MEDIUM", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:N", "integrityImpact": "LOW", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "NONE", "privilegesRequired": "LOW", "confidentialityImpact": "LOW"}, "impactScore": 2.5, "exploitabilityScore": 2.8}], "cvssMetricV40": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 5.3, "Automatable": "NOT_DEFINED", "attackVector": "NETWORK", "baseSeverity": "MEDIUM", "valueDensity": "NOT_DEFINED", "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:N/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", "exploitMaturity": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED", "userInteraction": "NONE", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "LOW", "subIntegrityImpact": "NONE", "vulnIntegrityImpact": "LOW", "integrityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "subAvailabilityImpact": "NONE", "vulnAvailabilityImpact": "NONE", "availabilityRequirement": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "subConfidentialityImpact": "NONE", "vulnConfidentialityImpact": "LOW", "confidentialityRequirement": "NOT_DEFINED", "modifiedAttackRequirements": "NOT_DEFINED", "modifiedPrivilegesRequired": "NOT_DEFINED", "modifiedSubIntegrityImpact": "NOT_DEFINED", "modifiedVulnIntegrityImpact": "NOT_DEFINED", "vulnerabilityResponseEffort": "NOT_DEFINED", "modifiedSubAvailabilityImpact": "NOT_DEFINED", "modifiedVulnAvailabilityImpact": "NOT_DEFINED", "modifiedSubConfidentialityImpact": "NOT_DEFINED", "modifiedVulnConfidentialityImpact": "NOT_DEFINED"}}]}, "affected": [{"source": "disclosure@vulncheck.com", "affectedData": [{"repo": "https://github.com/HKUDS/OpenHarness", "vendor": "HKUDS", "product": "OpenHarness", "versions": [{"status": "affected", "version": "0", "versionType": "semver", "lessThanOrEqual": "0.1.9"}, {"status": "unaffected", "version": "27bb93b810e9ea8fa4832eab7152eeb3b4a6bffb", "versionType": "git"}], "packageURL": "pkg:pypi/openharness-ai", "defaultStatus": "unaffected"}]}], "published": "2026-06-23T16:17:06.297", "references": [{"url": "https://github.com/HKUDS/OpenHarness/commit/27bb93b810e9ea8fa4832eab7152eeb3b4a6bffb", "source": "disclosure@vulncheck.com"}, {"url": "https://github.com/HKUDS/OpenHarness/pull/272", "source": "disclosure@vulncheck.com"}, {"url": "https://www.vulncheck.com/advisories/openharness-prompt-injection-via-issue-and-pr-comments-slash-commands", "source": "disclosure@vulncheck.com"}, {"url": "https://github.com/HKUDS/OpenHarness/pull/272", "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"}], "vulnStatus": "Deferred", "weaknesses": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "description": [{"lang": "en", "value": "CWE-862"}]}], "descriptions": [{"lang": "en", "value": "OpenHarness /issue and /pr_comments slash commands lack remote_invocable=False protection, allowing remote channel senders to write attacker-controlled Markdown into project context files. Admitted remote attackers can inject malicious content into .openharness/issue.md and .openharness/pr_comments.md files, which are subsequently injected into runtime system prompts, persistently influencing local agent behavior."}, {"lang": "es", "value": "Los comandos slash /issue y /pr_comments de OpenHarness carecen de protecci\u00f3n remote_invocable=False, lo que permite a los remitentes de canales remotos escribir Markdown controlado por el atacante en archivos de contexto del proyecto. Atacantes remotos admitidos pueden inyectar contenido malicioso en los archivos .openharness/issue.md y .openharness/pr_comments.md, los cuales son posteriormente inyectados en las indicaciones del sistema en tiempo de ejecuci\u00f3n, influyendo persistentemente en el comportamiento del agente local."}], "lastModified": "2026-10-25T23:10:00.167", "sourceIdentifier": "disclosure@vulncheck.com"}