{"id":"CVE-2026-22551","aliases":["GHSA-qwjm-9c66-w4q4"],"url":"https://o3.security/vulnerability/CVE-2026-22551","summary":"[Eclipse Theia] Data Exfiltration via Markdown Image Rendering in AI Chat","details":"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.","published":"2026-06-18T14:32:01.444Z","modified":"2026-08-12T03:51:19.983588611Z","cvss":null,"epss":{"score":0.00312,"percentile":0.23555,"asOf":"2026-09-01"},"cisaKev":null,"exploitsKnown":0,"affectedPackages":[{"ecosystem":"npm","name":"@theia/ai-chat-ui","fixedVersion":"1.71.0"},{"ecosystem":"npm","name":"@theia/ai-chat","fixedVersion":"1.71.0"},{"ecosystem":"npm","name":"@theia/ai-claude-code","fixedVersion":"1.71.0"},{"ecosystem":"npm","name":"@theia/ai-code-completion","fixedVersion":"1.71.0"},{"ecosystem":"npm","name":"@theia/ai-core","fixedVersion":"1.71.0"},{"ecosystem":"npm","name":"@theia/ai-editor","fixedVersion":"1.71.0"},{"ecosystem":"npm","name":"@theia/ai-ide","fixedVersion":"1.71.0"}],"fix":null,"references":[{"type":"WEB","url":"https://gitlab.eclipse.org/security/cve-assignment/-/work_items/115"},{"type":"ADVISORY","url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/22xxx/CVE-2026-22551.json"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-22551"},{"type":"PACKAGE","url":"https://github.com/eclipse-theia/theia"}],"provenance":{"sources":["OSV.dev","FIRST.org (EPSS)"],"lastVerified":"2026-08-12T03:51:19.983588611Z"}}