AAK-MCP-DBTMCP-CVE-2026-44968-001: dbt-mcp flag injection + tool-arg leakage (dbt-mcp below 1.17.1)
- Severity
- MEDIUM
- Category
- Supply Chain (
supply-chain) - Scanner
agent_audit_kit/scanners/mcp_cve_pins_2026_07.py- Auto-fixable
- No.
- SARIF name
DbtMcpFlagInjection
What it detects
dbt-mcp before 1.17.1 appends unsanitized node_selection / resource_type values to the dbt subprocess argv, letting an MCP client inject dbt global flags such as --profiles-dir / --project-dir / --target into subprocess.Popen even with shell=False (CVE-2026-44968); it also emits every tool call's full arguments (sql_query, vars, node_selection) through telemetry (CVE-2026-44970, on by default) and file logging (CVE-2026-44969) without redaction. Treat < 1.17.1 (and unpinned) as exposed.
How to fix
Upgrade dbt-mcp to >= 1.17.1 and pin it. Validate node_selection / resource_type against an allow-list before adding them to argv, and redact tool arguments in telemetry / logs.
To confirm the finding is gone, report only this rule:
agent-audit-kit scan . --rules AAK-MCP-DBTMCP-CVE-2026-44968-001
Limitations
Reads dbt-mcp in requirements*.txt at any depth and, at the project root only, in pyproject.toml, Pipfile, package.json, .mcp.json, mcp.json, claude_desktop_config.json and the Pipfile.lock, poetry.lock, uv.lock, package-lock.json, pnpm-lock.yaml and yarn.lock lockfiles, taking the lowest version a range allows and reporting a reference that states no version. The dependency is not read when it is declared in a sub-directory manifest (services/api/pyproject.toml), in .cursor/mcp.json or .vscode/mcp.json, or in a lockfile format the reader does not parse (pdm.lock). A file over 2 MB, or a lockfile over 32 MiB, is not read. A declaration nested more than 64 levels deep in package.json, a TOML manifest or an MCP config (an MCP server more than 62) is still judged, and reported without a line; a lockfile entry keeps its line at any depth.
References
- CVE: CVE-2026-44968, CVE-2026-44970, CVE-2026-44969, CVE-2026-55837
- OWASP MCP Top 10: MCP01:2025 (Token Mismanagement & Secret Exposure), MCP04:2025 (Software Supply Chain Attacks & Dependency Tampering), MCP05:2025 (Command Injection & Execution)
- OWASP Agentic Top 10: ASI02 (Tool Misuse and Exploitation), ASI04 (Agentic Supply Chain Vulnerabilities)
- Adversa AI MCP Top 25 (AAK-defined ids): ADV-INJECT-01 (Shell Injection via MCP)
- CSA AI Controls Matrix (AICM): AIS-07, DSP-17, STA-08
All rules. This page is generated from the rule registry when the documentation is built; to change it, change the rule in agent_audit_kit/rules/builtin.py. To give the rule a hand-written write-up, add docs/rules/AAK-MCP-DBTMCP-CVE-2026-44968-001.md: the page then shows that text, with the registry reference appended under it.