{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-22551", "assignerOrgId": "e51fbebd-6053-4e49-959f-1b94eeb69a2c", "state": "PUBLISHED", "assignerShortName": "eclipse", "dateReserved": "2026-05-22T07:47:58.210Z", "datePublished": "2026-06-18T14:32:01.444Z", "dateUpdated": "2026-06-18T15:25:13.612Z"}, "containers": {"cna": {"providerMetadata": {"orgId": "e51fbebd-6053-4e49-959f-1b94eeb69a2c", "shortName": "eclipse", "dateUpdated": "2026-06-18T14:32:01.444Z"}, "problemTypes": [{"descriptions": [{"lang": "en", "cweId": "CWE-201", "description": "CWE-201: Insertion of Sensitive Information Into Sent Data", "type": "CWE"}]}, {"descriptions": [{"lang": "en", "cweId": "CWE-829", "description": "CWE-829: Inclusion of Functionality from Untrusted Control Sphere", "type": "CWE"}]}], "affected": [{"vendor": "Eclipse Foundation", "product": "Eclipse Theia", "repo": "https://github.com/eclipse-theia/theia", "versions": [{"status": "affected", "version": "0", "lessThan": "1.71.0", "versionType": "semver"}], "defaultStatus": "unaffected"}], "descriptions": [{"lang": "en", "value": "In Eclipse Theia versions prior to 1.71.0, the AI chat rendered Markdown image tags from AI responses, triggering HTTP requests to arbitrary external URLs without restriction. Combined with prompt injection in a malicious workspace, an attacker could induce the AI agent to construct image URLs encoding sensitive information from the workspace or conversation context, exfiltrating it to attacker-controlled servers. The workspace trust enforcement introduced in v1.71.0 mitigates the documented attack chain by disabling AI features in untrusted workspaces.", "supportingMedia": [{"type": "text/html", "base64": false, "value": "In Eclipse Theia versions prior to 1.71.0, the AI chat rendered Markdown image tags from AI responses, triggering HTTP requests to arbitrary external URLs without restriction. Combined with prompt injection in a malicious workspace, an attacker could induce the AI agent to construct image URLs encoding sensitive information from the workspace or conversation context, exfiltrating it to attacker-controlled servers. The workspace trust enforcement introduced in v1.71.0 mitigates the documented attack chain by disabling AI features in untrusted workspaces."}]}], "references": [{"url": "https://gitlab.eclipse.org/security/cve-assignment/-/work_items/115"}], "metrics": [{"format": "CVSS", "scenarios": [{"lang": "en", "value": "GENERAL"}], "cvssV4_0": {"attackVector": "LOCAL", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "NONE", "userInteraction": "ACTIVE", "vulnConfidentialityImpact": "HIGH", "subConfidentialityImpact": "NONE", "vulnIntegrityImpact": "NONE", "subIntegrityImpact": "NONE", "vulnAvailabilityImpact": "NONE", "subAvailabilityImpact": "NONE", "exploitMaturity": "NOT_DEFINED", "Safety": "NOT_DEFINED", "Automatable": "NOT_DEFINED", "Recovery": "NOT_DEFINED", "valueDensity": "NOT_DEFINED", "vulnerabilityResponseEffort": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED", "version": "4.0", "baseSeverity": "MEDIUM", "baseScore": 6.7, "vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N"}}], "credits": [{"lang": "en", "value": "Piotr Ryciak (https://gitlab.eclipse.org/void01)", "type": "finder"}], "source": {"discovery": "UNKNOWN"}, "x_generator": {"engine": "Vulnogram 1.0.2"}}, "adp": [{"metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2026-06-18T15:25:00.091475Z", "id": "CVE-2026-22551", "options": [{"Exploitation": "none"}, {"Automatable": "no"}, {"Technical Impact": "partial"}], "role": "CISA Coordinator", "version": "2.0.3"}}}], "title": "CISA ADP Vulnrichment", "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-06-18T15:25:13.612Z"}}]}}

{"dataType": "CVE_RECORD", "containers": {"adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2026-22551", "role": "CISA Coordinator", "options": [{"Exploitation": "none"}, {"Automatable": "no"}, {"Technical Impact": "partial"}], "version": "2.0.3", "timestamp": "2026-06-18T15:25:00.091475Z"}}}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-06-18T15:25:06.566Z"}}], "cna": {"source": {"discovery": "UNKNOWN"}, "credits": [{"lang": "en", "type": "finder", "value": "Piotr Ryciak (https://gitlab.eclipse.org/void01)"}], "metrics": [{"format": "CVSS", "cvssV4_0": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 6.7, "Automatable": "NOT_DEFINED", "attackVector": "LOCAL", "baseSeverity": "MEDIUM", "valueDensity": "NOT_DEFINED", "vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N", "exploitMaturity": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED", "userInteraction": "ACTIVE", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "NONE", "subIntegrityImpact": "NONE", "vulnIntegrityImpact": "NONE", "subAvailabilityImpact": "NONE", "vulnAvailabilityImpact": "NONE", "subConfidentialityImpact": "NONE", "vulnConfidentialityImpact": "HIGH", "vulnerabilityResponseEffort": "NOT_DEFINED"}, "scenarios": [{"lang": "en", "value": "GENERAL"}]}], "affected": [{"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"}], "references": [{"url": "https://gitlab.eclipse.org/security/cve-assignment/-/work_items/115"}], "x_generator": {"engine": "Vulnogram 1.0.2"}, "descriptions": [{"lang": "en", "value": "In Eclipse Theia versions prior to 1.71.0, the AI chat rendered Markdown image tags from AI responses, triggering HTTP requests to arbitrary external URLs without restriction. Combined with prompt injection in a malicious workspace, an attacker could induce the AI agent to construct image URLs encoding sensitive information from the workspace or conversation context, exfiltrating it to attacker-controlled servers. The workspace trust enforcement introduced in v1.71.0 mitigates the documented attack chain by disabling AI features in untrusted workspaces.", "supportingMedia": [{"type": "text/html", "value": "In Eclipse Theia versions prior to 1.71.0, the AI chat rendered Markdown image tags from AI responses, triggering HTTP requests to arbitrary external URLs without restriction. Combined with prompt injection in a malicious workspace, an attacker could induce the AI agent to construct image URLs encoding sensitive information from the workspace or conversation context, exfiltrating it to attacker-controlled servers. The workspace trust enforcement introduced in v1.71.0 mitigates the documented attack chain by disabling AI features in untrusted workspaces.", "base64": false}]}], "problemTypes": [{"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-201", "description": "CWE-201: Insertion of Sensitive Information Into Sent Data"}]}, {"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-829", "description": "CWE-829: Inclusion of Functionality from Untrusted Control Sphere"}]}], "providerMetadata": {"orgId": "e51fbebd-6053-4e49-959f-1b94eeb69a2c", "shortName": "eclipse", "dateUpdated": "2026-06-18T14:32:01.444Z"}}}, "cveMetadata": {"cveId": "CVE-2026-22551", "state": "PUBLISHED", "dateUpdated": "2026-06-18T15:25:13.612Z", "dateReserved": "2026-05-22T07:47:58.210Z", "assignerOrgId": "e51fbebd-6053-4e49-959f-1b94eeb69a2c", "datePublished": "2026-06-18T14:32:01.444Z", "assignerShortName": "eclipse"}, "dataVersion": "5.2"}

{}

{}

{"affected": [{"configurations": [{"platform": null, "status": "affected", "versions": {"scheme": "semver", "value": "[0,1.71.0)"}}], "enrichment": {"confidence": 95.0, "confidence_source": "inferred", "scores": [{"score": 95.0, "source": "inferred"}, {"score": 100.0, "source": "matching"}]}, "original": {"product": "Eclipse Theia", "source": "cna", "vendor": "Eclipse Foundation"}, "product": "theia", "vendor": "eclipse"}], "created": "2026-06-18T18:30:15.037220+00:00", "title": "Eclipse Theia AI Chat Exposes Workspace Data via Unrestricted External Image Requests", "updated": "2026-06-18T19:15:02.432361+00:00", "vendors": ["eclipse", "eclipse$PRODUCT$theia"]}