GHSA-M973-PR9R-HP2W

Vulnerability from github – Published: 2026-06-18 18:35 – Updated: 2026-06-19 19:20
VLAI
Summary
[Eclipse Theia] Indirect Prompt Injection via Auto-Loaded Workspace Prompt Template Files in AI Chat
Details

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.

Severity
8.4 (High)
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
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "npm",
        "name": "@theia/ai-chat-ui"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.71.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "npm",
        "name": "@theia/ai-chat"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.71.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "npm",
        "name": "@theia/ai-claude-code"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.71.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "npm",
        "name": "@theia/ai-code-completion"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.71.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "npm",
        "name": "@theia/ai-core"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.71.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "npm",
        "name": "@theia/ai-editor"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.71.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-46580"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-829"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-06-19T19:20:46Z",
    "nvd_published_at": "2026-06-18T16:16:54Z",
    "severity": "HIGH"
  },
  "details": "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\u0027s system prompts. An attacker could craft a malicious repository containing prompt template files that, when the workspace was opened in Theia, replaced the AI\u0027s 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.",
  "id": "GHSA-m973-pr9r-hp2w",
  "modified": "2026-06-19T19:20:46Z",
  "published": "2026-06-18T18:35:23Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-46580"
    },
    {
      "type": "WEB",
      "url": "https://github.com/eclipse-theia/theia/issues/16892"
    },
    {
      "type": "WEB",
      "url": "https://github.com/eclipse-theia/theia/pull/17364"
    },
    {
      "type": "WEB",
      "url": "https://github.com/eclipse-theia/theia/commit/e3fdfe6992389bc5fa611058d00c39d7408508ed"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/eclipse-theia/theia"
    },
    {
      "type": "WEB",
      "url": "https://gitlab.eclipse.org/security/cve-assignment/-/work_items/114"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "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",
      "type": "CVSS_V4"
    }
  ],
  "summary": "[Eclipse Theia] Indirect Prompt Injection via Auto-Loaded Workspace Prompt Template Files in AI Chat"
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.



Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.