CVE-2026-44688

In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its prompt context without distinguishing them from system instructions. An attacker could craft a malicious repository with adversarial directory or file names that, when analyzed by the AI agent, would cause the agent to follow attacker-controlled instructions (indirect prompt injection). Combined with other AI chat features available in untrusted workspaces, this enabled attack chains leading to data exfiltration via Markdown image rendering or arbitrary command execution via task definitions.

CVSS

No CVSS.

References

Link	Resource
https://gitlab.eclipse.org/security/cve-assignment/-/work_items/113

Configurations

No configuration.

History

19 Jun 2026, 06:17

Type	Values Removed	Values Added
New CVE

Information

Published : 2026-06-18 16:16

Updated : 2026-06-22 17:53

NVD link : CVE-2026-44688

Mitre link : CVE-2026-44688

CVE.ORG link : CVE-2026-44688

JSON object : View

Products Affected

No product.

CWE

CWE-829

Inclusion of Functionality from Untrusted Control Sphere

{"id": "CVE-2026-44688", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-44688", "role": "CISA Coordinator", "options": [{"exploitation": "none"}, {"automatable": "no"}, {"technicalImpact": "total"}], "version": "2.0.3", "timestamp": "2026-06-18T00:00:00+00:00"}}], "cvssMetricV40": [{"type": "Secondary", "source": "emo@eclipse.org", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 8.4, "Automatable": "NOT_DEFINED", "attackVector": "LOCAL", "baseSeverity": "HIGH", "valueDensity": "NOT_DEFINED", "vectorString": "CVSS:4.0/AV:L/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", "exploitMaturity": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED", "userInteraction": "ACTIVE", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "NONE", "subIntegrityImpact": "NONE", "vulnIntegrityImpact": "HIGH", "integrityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "subAvailabilityImpact": "NONE", "vulnAvailabilityImpact": "HIGH", "availabilityRequirement": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "subConfidentialityImpact": "NONE", "vulnConfidentialityImpact": "HIGH", "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": "emo@eclipse.org", "affectedData": [{"repo": "https://github.com/eclipse-theia/theia", "vendor": "Eclipse Foundation", "product": "Eclipse Theia", "versions": [{"status": "affected", "version": "0", "lessThan": "1.71.0", "versionType": "semver"}], "defaultStatus": "unaffected"}]}], "published": "2026-06-18T16:16:53.977", "references": [{"url": "https://gitlab.eclipse.org/security/cve-assignment/-/work_items/113", "source": "emo@eclipse.org"}], "vulnStatus": "Undergoing Analysis", "weaknesses": [{"type": "Secondary", "source": "emo@eclipse.org", "description": [{"lang": "en", "value": "CWE-829"}]}], "descriptions": [{"lang": "en", "value": "In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its prompt context without distinguishing them from system instructions. An attacker could craft a malicious repository with adversarial directory or file names that, when analyzed by the AI agent, would cause the agent to follow attacker-controlled instructions (indirect prompt injection). Combined with other AI chat features available in untrusted workspaces, this enabled attack chains leading to data exfiltration via Markdown image rendering or arbitrary command execution via task definitions."}], "lastModified": "2026-06-22T17:53:07.283", "sourceIdentifier": "emo@eclipse.org"}