{"items":[{"id":"NVI-00018663","kind":"vulnerability","title":"[Eclipse Theia] Indirect Prompt Injection via Auto-Loaded Workspace Prompt Template Files in AI Chat","revision":1,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-m973-pr9r-hp2w","CVE-2026-46580"],"plain_summary":"GitHub lists this reviewed advisory for @theia/ai-chat-ui, @theia/ai-chat, @theia/ai-claude-code, @theia/ai-code-completion, @theia/ai-core. Published version ranges and source prerequisites are shown below; this is not an inspection of a visitor’s application.","review_status":"source_listed","control_topics":[],"public_actions":[{"summary":"Identify the exact component and deployed version, examine the linked publisher’s conditions, and retain evidence of any mitigation.","source_ids":["sr-4cd9e10ded1b701d610e4e5bb260b365"],"action_type":"investigate","limitations":"Confirm current vendor support, compatibility and deployment evidence. This report has not tested a fix in your system.","current_supported_target":null}],"schema_version":"1.1.0","source_metrics":[],"why_it_matters":"Published affected context helps an owner decide what evidence to gather. This report has not examined your application.","related_sources":[{"id":"sr-4cd9e10ded1b701d610e4e5bb260b365","url":"https://github.com/advisories/GHSA-m973-pr9r-hp2w","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-m973-pr9r-hp2w","publisher":"GitHub Advisory Database","observed_at":"2026-11-06T07:19:16.585Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-4cd9e10ded1b701d610e4e5bb260b365"],"technology":"@theia/ai-chat-ui","known_exclusions":[],"conditions_summary":"In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/*.prompttemplate in a workspace were automatically loaded and could override or extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the workspace was opened in Theia, replaced the AI's system instructions with attacker-controlled content (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.","public_affected_ranges":["< 1.71.0"]},{"certainty":"source_listed","source_ids":["sr-4cd9e10ded1b701d610e4e5bb260b365"],"technology":"@theia/ai-chat","known_exclusions":[],"conditions_summary":"In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/*.prompttemplate in a workspace were automatically loaded and could override or extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the workspace was opened in Theia, replaced the AI's system instructions with attacker-controlled content (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.","public_affected_ranges":["< 1.71.0"]},{"certainty":"source_listed","source_ids":["sr-4cd9e10ded1b701d610e4e5bb260b365"],"technology":"@theia/ai-claude-code","known_exclusions":[],"conditions_summary":"In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/*.prompttemplate in a workspace were automatically loaded and could override or extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the workspace was opened in Theia, replaced the AI's system instructions with attacker-controlled content (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.","public_affected_ranges":["< 1.71.0"]},{"certainty":"source_listed","source_ids":["sr-4cd9e10ded1b701d610e4e5bb260b365"],"technology":"@theia/ai-code-completion","known_exclusions":[],"conditions_summary":"In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/*.prompttemplate in a workspace were automatically loaded and could override or extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the workspace was opened in Theia, replaced the AI's system instructions with attacker-controlled content (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.","public_affected_ranges":["< 1.71.0"]},{"certainty":"source_listed","source_ids":["sr-4cd9e10ded1b701d610e4e5bb260b365"],"technology":"@theia/ai-core","known_exclusions":[],"conditions_summary":"In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/*.prompttemplate in a workspace were automatically loaded and could override or extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the workspace was opened in Theia, replaced the AI's system instructions with attacker-controlled content (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.","public_affected_ranges":["< 1.71.0"]},{"certainty":"source_listed","source_ids":["sr-4cd9e10ded1b701d610e4e5bb260b365"],"technology":"@theia/ai-editor","known_exclusions":[],"conditions_summary":"In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/*.prompttemplate in a workspace were automatically loaded and could override or extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the workspace was opened in Theia, replaced the AI's system instructions with attacker-controlled content (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.","public_affected_ranges":["< 1.71.0"]}],"null_published_at":"2026-11-07T07:07:42.452Z","source_updated_at":"2026-06-19T19:20:47.000Z","source_disclosed_at":"2026-06-18T18:35:23.000Z","is_synthetic_fixture":false,"null_last_reviewed_at":null,"public_change_summary":"First indexed by Null; source disclosure date is shown separately.","null_first_observed_at":"2026-11-06T07:19:16.585Z"}],"next_cursor":null,"snapshot_revision":"42594"}