AAK-MCP-AGENTICFLOW-CVE-2026-58195-001: Agentic-Flow MCP tool params → execSync command injection (below 2.0.14)
- Severity
- HIGH
- Category
- Supply Chain (
supply-chain) - Scanner
agent_audit_kit/scanners/mcp_cve_pins_2026_07.py- Auto-fixable
- No.
- SARIF name
AgenticFlowMcpExecSyncInjection
What it detects
agentic-flow before 2.0.14 interpolates attacker-influenceable MCP tool parameters (agent, task, name, language, agentdb) directly into shell command strings passed to execSync() across its stdio / FastMCP server and agent/swarm/hooks tools, allowing arbitrary OS command execution as the MCP server user (CVE-2026-58195, CVSS 8.8). Treat < 2.0.14 (and unpinned) as exposed.
How to fix
Upgrade agentic-flow to >= 2.0.14 and pin it. Never pass tool parameters into a shell; use argv-array subprocess calls with validated inputs.
To confirm the finding is gone, report only this rule:
agent-audit-kit scan . --rules AAK-MCP-AGENTICFLOW-CVE-2026-58195-001
Limitations
Reads agentic-flow 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 (packages/app/package.json), in .cursor/mcp.json or .vscode/mcp.json, or in a lockfile format the reader does not parse (a Yarn 2+ yarn.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-2026-58195
- OWASP MCP Top 10: MCP04:2025 (Software Supply Chain Attacks & Dependency Tampering), MCP05:2025 (Command Injection & Execution)
- OWASP Agentic Top 10: ASI04 (Agentic Supply Chain Vulnerabilities), ASI05 (Unexpected Code Execution (RCE))
- Adversa AI MCP Top 25 (AAK-defined ids): ADV-INJECT-01 (Shell Injection via MCP)
- CSA AI Controls Matrix (AICM): AIS-07, 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-AGENTICFLOW-CVE-2026-58195-001.md: the page then shows that text, with the registry reference appended under it.