{"id":"CVE-2026-58195","aliases":["EUVD-2026-45256","GHSA-vcv2-r9jh-99m5"],"status":"published","title":"Agentic-Flow: OS Command Injection in agentic-flow MCP server tools via unsanitized tool-parameter interpolation into execSync","description":"Agentic-Flow is an AI agent orchestration platform. Prior to 2.0.14, agentic-flow MCP server tools in src/mcp/standalone-stdio.ts, src/mcp/fastmcp/servers/claude-flow-sdk.ts, src/mcp/fastmcp/servers/stdio-full.ts, src/mcp/fastmcp/servers/http-streaming-updated.ts, src/mcp/fastmcp/servers/http-sse.ts, src/mcp/fastmcp/servers/poc-stdio.ts, src/mcp/fastmcp/tools/agent/{execute,list,parallel}.ts, src/mcp/fastmcp/tools/swarm/orchestrate.ts, and src/mcp/fastmcp/tools/hooks/pretrain.ts interpolated attacker-influenceable tool parameters such as agent, task, name, language, and agentdb directly into shell command strings passed to execSync(), allowing arbitrary OS command execution with the privileges of the MCP server user. This issue is fixed in version 2.0.14.","severity":{"version":"3.1","score":8.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-12","score":0.00562,"percentile":0.47232,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":true},"cwes":["CWE-78"],"published":"2026-06-19T15:12:58Z","modified":"2026-10-28T02:30:51Z","fixes":[{"ecosystem":"npm","package":"agentic-flow","fixed_in":["2.0.14"],"sources":["ghsa","osv"]}],"affected":[{"source":"ghsa","ecosystem":"npm","package":"agentic-flow","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"2.0.13"},{"fixed":"2.0.14"}]}]},{"source":"osv","ecosystem":"npm","package":"agentic-flow","ranges":[{"type":"SEMVER","events":[{"introduced":"0"},{"fixed":"2.0.14"}]}]}],"products":[{"vendor":"ruvnet","product":"agentic-flow"}],"references":[{"url":"https://github.com/ruvnet/agentic-flow/security/advisories/GHSA-vcv2-r9jh-99m5","tags":["x_refsource_CONFIRM","exploit","advisory","web"]},{"url":"https://github.com/ruvnet/agentic-flow/issues/169","tags":["x_refsource_MISC","report","web"]},{"url":"https://github.com/ruvnet/ruflo/issues/2414","tags":["x_refsource_MISC","report","web"]},{"url":"https://github.com/ruvnet/agentic-flow/pull/170","tags":["x_refsource_MISC","fix","web"]},{"url":"https://github.com/ruvnet/ruflo/pull/2415","tags":["x_refsource_MISC","fix","web"]},{"url":"https://github.com/ruvnet/agentic-flow/commit/0c2ec967736a8b6b85832c6bae2a3e74989705ec","tags":["x_refsource_MISC","fix"]},{"url":"https://github.com/ruvnet/ruflo/releases/tag/v3.12.4","tags":["x_refsource_MISC","web"]},{"url":"https://www.npmjs.com/package/agentic-flow/v/2.0.14","tags":["web"]},{"url":"https://github.com/advisories/GHSA-vcv2-r9jh-99m5"},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/58xxx/CVE-2026-58195.json","tags":["advisory"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-58195","tags":["advisory"]},{"url":"https://github.com/ruvnet/agentic-flow","tags":["package"]}],"sources":{"cve":[{"id":"CVE-2026-58195","title":"Agentic-Flow: OS Command Injection in agentic-flow MCP server tools via unsanitized tool-parameter interpolation into execSync","description":"Agentic-Flow is an AI agent orchestration platform. Prior to 2.0.14, agentic-flow MCP server tools in src/mcp/standalone-stdio.ts, src/mcp/fastmcp/servers/claude-flow-sdk.ts, src/mcp/fastmcp/servers/stdio-full.ts, src/mcp/fastmcp/servers/http-streaming-updated.ts, src/mcp/fastmcp/servers/http-sse.ts, src/mcp/fastmcp/servers/poc-stdio.ts, src/mcp/fastmcp/tools/agent/{execute,list,parallel}.ts, src/mcp/fastmcp/tools/swarm/orchestrate.ts, and src/mcp/fastmcp/tools/hooks/pretrain.ts interpolated attacker-influenceable tool parameters such as agent, task, name, language, and agentdb directly into shell command strings passed to execSync(), allowing arbitrary OS command execution with the privileges of the MCP server user. This issue is fixed in version 2.0.14.","status":"published","published":"2026-07-17T18:47:05.179Z","modified":"2026-07-17T19:19:01.284Z","cvss":[{"version":"3.1","score":8.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high","assessor":"cna"}],"cwes":["CWE-78"],"updated_at":"2026-11-02T13:47:28.691429Z"}],"euvd":[{"id":"EUVD-2026-45256","description":"Agentic-Flow is an AI agent orchestration platform. Prior to 2.0.14, agentic-flow MCP server tools in src/mcp/standalone-stdio.ts, src/mcp/fastmcp/servers/claude-flow-sdk.ts, src/mcp/fastmcp/servers/stdio-full.ts, src/mcp/fastmcp/servers/http-streaming-updated.ts, src/mcp/fastmcp/servers/http-sse.ts, src/mcp/fastmcp/servers/poc-stdio.ts, src/mcp/fastmcp/tools/agent/{execute,list,parallel}.ts, src/mcp/fastmcp/tools/swarm/orchestrate.ts, and src/mcp/fastmcp/tools/hooks/pretrain.ts interpolated attacker-influenceable tool parameters such as agent, task, name, language, and agentdb directly into shell command strings passed to execSync(), allowing arbitrary OS command execution with the privileges of the MCP server user. This issue is fixed in version 2.0.14.","status":"published","published":"2026-07-17T18:47:05Z","modified":"2026-07-17T19:19:01Z","cvss":[{"version":"3.1","score":8.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high"}],"updated_at":"2026-11-02T18:19:50.451546Z"}],"ghsa":[{"id":"GHSA-vcv2-r9jh-99m5","title":"Agentic-Flow: OS Command Injection in agentic-flow MCP server tools via unsanitized tool-parameter interpolation into execSync","description":"## Summary\n\n`agentic-flow` versions `\u003c= 2.0.13` MCP server tools interpolated attacker-influenceable tool parameters (e.g. `agent`, `task`, `name`, `language`, `agentdb` arguments) directly into shell command strings passed to `execSync()`. A malicious value reaching any of the affected MCP tools could break out of the surrounding double-quoted argument and execute arbitrary OS commands with the privileges of the user running the MCP server.\n\nThis was a partial-fix gap: prior commit `6a06854` (#158) fixed CWE-78 elsewhere in the project but missed the MCP server files entirely.\n\n## Impact\n\nAny MCP tool argument that the AI agent treats as data but the implementation interpolates into a shell command string becomes a command-injection vector. In MCP deployments where untrusted content (web pages, files, third-party tool output) is processed by the agent, this is reachable without direct attacker access to the host. The HTTP/SSE transports (`http-sse.ts`, `http-streaming-updated.ts`) expose the same sinks without authentication or Origin/Host validation, which may raise the effective severity in any deployment that binds them to a reachable network interface.\n\n## Affected components\n\n- `src/mcp/standalone-stdio.ts` — `agentic_flow_agent`, `agentic_flow_create_agent`, `agentic_flow_list_all_agents`, `agentic_flow_agent_info`, `agentic_flow_check_conflicts`, `agentic_flow_optimize_model`, `agentic_flow_list_agents`, `agent_booster_edit_file`, `agent_booster_batch_edit`, `agent_booster_parse_markdown`, `agentdb_stats`, `agentdb_pattern_store`, `agentdb_pattern_search`, `agentdb_pattern_stats`\n- `src/mcp/fastmcp/servers/claude-flow-sdk.ts`\n- `src/mcp/fastmcp/servers/stdio-full.ts`\n- `src/mcp/fastmcp/servers/http-streaming-updated.ts`\n- `src/mcp/fastmcp/servers/http-sse.ts`\n- `src/mcp/fastmcp/servers/poc-stdio.ts`\n- `src/mcp/fastmcp/tools/agent/{execute,list,parallel}.ts`\n- `src/mcp/fastmcp/tools/swarm/orchestrate.ts`\n- `src/mcp/fastmcp/tools/hooks/pretrain.ts` (depth path only)\n\n## Proof of Concept\n\n```ts\n// Pre-fix (standalone-stdio.ts, agentic_flow_agent)\nlet cmd = `npx --yes agentic-flow --agent \"${agent}\" --task \"${task}\"`;\nconst result = execSync(cmd, { encoding: 'utf-8', ... });\n```\n\nInvoking the MCP tool with:\n\n```json\n{\n  \"agent\": \"coder\",\n  \"task\": \"x\\\"; touch /tmp/INJECTED; id \u003e /tmp/rce.txt; echo \\\"\"\n}\n```\n\nproduces, after interpolation:\n\n```\nnpx --yes agentic-flow --agent \"coder\" --task \"x\"; touch /tmp/INJECTED; id \u003e /tmp/rce.txt; echo \"\"\n```\n\nWhen `execSync` hands that to `/bin/sh -c`, the shell parses three commands: the truncated `npx`, then `touch /tmp/INJECTED`, then `id \u003e /tmp/rce.txt; echo \"\"`. The marker file `/tmp/INJECTED` is created and the user's `id` output is written to `/tmp/rce.txt`.\n\n## Patches\n\nFixed in [`agentic-flow@2.0.14`](https://www.npmjs.com/package/agentic-flow/v/2.0.14) — every affected call site rewritten to use `execFileSync(file, argv, { shell: false })` so attacker-controlled argv elements are passed straight to `execve(2)` without shell parsing.\n\nFix PR: ruvnet/agentic-flow#170 (merged at `0c2ec96`)\n\nA regression test (`tests/security/cwe-78-mcp-execsync.test.ts`) was added that statically scans every `src/mcp/**/*.ts` file and fails the build if any new `execSync()` call is reintroduced outside of a documented exemption, plus a behavioural smoke check that the canonical PoC payload remains inert when passed as an argv element to `execFileSync`.\n\n## Workarounds\n\nUpgrade to `agentic-flow \u003e= 2.0.14`. There is no in-product configuration that mitigates this without upgrading.\n\n## Downstream pin\n\nThe `ruflo` / `claude-flow` / `@claude-flow/cli` packages bumped from `3.12.3` → `3.12.4` to pull the patched `agentic-flow`:\n\n- `ruflo@3.12.4`\n- `claude-flow@3.12.4`\n- `@claude-flow/cli@3.12.4`\n\nEnd users running any of `npx ruflo@latest`, `npx claude-flow@latest`, or `npx @claude-flow/cli@latest` are pinned to the fixed version.\n\n## Credit\n\nReported by **hackchang** via a well-scoped red-team report package (`npm_agentic-flow_report_package_20260618_163017.zip`) that included a sink inventory, a minimized PoC payload, and a clear explanation of why this was a partial-fix gap rather than intended behaviour. The sink inventory directly drove the single-grep pass that closed every reachable call site; the PoC payload became the behavioural smoke test that proves the canonical attack stays inert as an argv element.","status":"published","published":"2026-06-19T15:12:58Z","modified":"2026-06-19T15:13:00Z","cvss":[{"version":"3.1","score":8.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high"}],"cwes":["CWE-78"],"updated_at":"2026-11-02T14:40:30.53004Z"}],"nvd":[{"id":"CVE-2026-58195","description":"Agentic-Flow is an AI agent orchestration platform. Prior to 2.0.14, agentic-flow MCP server tools in src/mcp/standalone-stdio.ts, src/mcp/fastmcp/servers/claude-flow-sdk.ts, src/mcp/fastmcp/servers/stdio-full.ts, src/mcp/fastmcp/servers/http-streaming-updated.ts, src/mcp/fastmcp/servers/http-sse.ts, src/mcp/fastmcp/servers/poc-stdio.ts, src/mcp/fastmcp/tools/agent/{execute,list,parallel}.ts, src/mcp/fastmcp/tools/swarm/orchestrate.ts, and src/mcp/fastmcp/tools/hooks/pretrain.ts interpolated attacker-influenceable tool parameters such as agent, task, name, language, and agentdb directly into shell command strings passed to execSync(), allowing arbitrary OS command execution with the privileges of the MCP server user. This issue is fixed in version 2.0.14.","status":"published","published":"2026-07-17T19:17:17.41Z","modified":"2026-10-24T20:10:00.137Z","cvss":[{"version":"3.1","score":8.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high","assessor":"secondary"}],"cwes":["CWE-78"],"updated_at":"2026-11-02T14:12:30.250437Z"}],"osv":[{"id":"CVE-2026-58195","title":"Agentic-Flow: OS Command Injection in agentic-flow MCP server tools via unsanitized tool-parameter interpolation into execSync","description":"Agentic-Flow is an AI agent orchestration platform. Prior to 2.0.14, agentic-flow MCP server tools in src/mcp/standalone-stdio.ts, src/mcp/fastmcp/servers/claude-flow-sdk.ts, src/mcp/fastmcp/servers/stdio-full.ts, src/mcp/fastmcp/servers/http-streaming-updated.ts, src/mcp/fastmcp/servers/http-sse.ts, src/mcp/fastmcp/servers/poc-stdio.ts, src/mcp/fastmcp/tools/agent/{execute,list,parallel}.ts, src/mcp/fastmcp/tools/swarm/orchestrate.ts, and src/mcp/fastmcp/tools/hooks/pretrain.ts interpolated attacker-influenceable tool parameters such as agent, task, name, language, and agentdb directly into shell command strings passed to execSync(), allowing arbitrary OS command execution with the privileges of the MCP server user. This issue is fixed in version 2.0.14.","status":"published","published":"2026-07-17T18:47:05.179Z","modified":"2026-10-28T02:30:51.597378794Z","cvss":[{"version":"3.1","score":8.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high"}],"cwes":["CWE-78"],"updated_at":"2026-11-02T15:45:12.016252Z"},{"id":"GHSA-vcv2-r9jh-99m5","title":"Agentic-Flow: OS Command Injection in agentic-flow MCP server tools via unsanitized tool-parameter interpolation into execSync","description":"## Summary\n\n`agentic-flow` versions `\u003c= 2.0.13` MCP server tools interpolated attacker-influenceable tool parameters (e.g. `agent`, `task`, `name`, `language`, `agentdb` arguments) directly into shell command strings passed to `execSync()`. A malicious value reaching any of the affected MCP tools could break out of the surrounding double-quoted argument and execute arbitrary OS commands with the privileges of the user running the MCP server.\n\nThis was a partial-fix gap: prior commit `6a06854` (#158) fixed CWE-78 elsewhere in the project but missed the MCP server files entirely.\n\n## Impact\n\nAny MCP tool argument that the AI agent treats as data but the implementation interpolates into a shell command string becomes a command-injection vector. In MCP deployments where untrusted content (web pages, files, third-party tool output) is processed by the agent, this is reachable without direct attacker access to the host. The HTTP/SSE transports (`http-sse.ts`, `http-streaming-updated.ts`) expose the same sinks without authentication or Origin/Host validation, which may raise the effective severity in any deployment that binds them to a reachable network interface.\n\n## Affected components\n\n- `src/mcp/standalone-stdio.ts` — `agentic_flow_agent`, `agentic_flow_create_agent`, `agentic_flow_list_all_agents`, `agentic_flow_agent_info`, `agentic_flow_check_conflicts`, `agentic_flow_optimize_model`, `agentic_flow_list_agents`, `agent_booster_edit_file`, `agent_booster_batch_edit`, `agent_booster_parse_markdown`, `agentdb_stats`, `agentdb_pattern_store`, `agentdb_pattern_search`, `agentdb_pattern_stats`\n- `src/mcp/fastmcp/servers/claude-flow-sdk.ts`\n- `src/mcp/fastmcp/servers/stdio-full.ts`\n- `src/mcp/fastmcp/servers/http-streaming-updated.ts`\n- `src/mcp/fastmcp/servers/http-sse.ts`\n- `src/mcp/fastmcp/servers/poc-stdio.ts`\n- `src/mcp/fastmcp/tools/agent/{execute,list,parallel}.ts`\n- `src/mcp/fastmcp/tools/swarm/orchestrate.ts`\n- `src/mcp/fastmcp/tools/hooks/pretrain.ts` (depth path only)\n\n## Proof of Concept\n\n```ts\n// Pre-fix (standalone-stdio.ts, agentic_flow_agent)\nlet cmd = `npx --yes agentic-flow --agent \"${agent}\" --task \"${task}\"`;\nconst result = execSync(cmd, { encoding: 'utf-8', ... });\n```\n\nInvoking the MCP tool with:\n\n```json\n{\n  \"agent\": \"coder\",\n  \"task\": \"x\\\"; touch /tmp/INJECTED; id \u003e /tmp/rce.txt; echo \\\"\"\n}\n```\n\nproduces, after interpolation:\n\n```\nnpx --yes agentic-flow --agent \"coder\" --task \"x\"; touch /tmp/INJECTED; id \u003e /tmp/rce.txt; echo \"\"\n```\n\nWhen `execSync` hands that to `/bin/sh -c`, the shell parses three commands: the truncated `npx`, then `touch /tmp/INJECTED`, then `id \u003e /tmp/rce.txt; echo \"\"`. The marker file `/tmp/INJECTED` is created and the user's `id` output is written to `/tmp/rce.txt`.\n\n## Patches\n\nFixed in [`agentic-flow@2.0.14`](https://www.npmjs.com/package/agentic-flow/v/2.0.14) — every affected call site rewritten to use `execFileSync(file, argv, { shell: false })` so attacker-controlled argv elements are passed straight to `execve(2)` without shell parsing.\n\nFix PR: ruvnet/agentic-flow#170 (merged at `0c2ec96`)\n\nA regression test (`tests/security/cwe-78-mcp-execsync.test.ts`) was added that statically scans every `src/mcp/**/*.ts` file and fails the build if any new `execSync()` call is reintroduced outside of a documented exemption, plus a behavioural smoke check that the canonical PoC payload remains inert when passed as an argv element to `execFileSync`.\n\n## Workarounds\n\nUpgrade to `agentic-flow \u003e= 2.0.14`. There is no in-product configuration that mitigates this without upgrading.\n\n## Downstream pin\n\nThe `ruflo` / `claude-flow` / `@claude-flow/cli` packages bumped from `3.12.3` → `3.12.4` to pull the patched `agentic-flow`:\n\n- `ruflo@3.12.4`\n- `claude-flow@3.12.4`\n- `@claude-flow/cli@3.12.4`\n\nEnd users running any of `npx ruflo@latest`, `npx claude-flow@latest`, or `npx @claude-flow/cli@latest` are pinned to the fixed version.\n\n## Credit\n\nReported by **hackchang** via a well-scoped red-team report package (`npm_agentic-flow_report_package_20260618_163017.zip`) that included a sink inventory, a minimized PoC payload, and a clear explanation of why this was a partial-fix gap rather than intended behaviour. The sink inventory directly drove the single-grep pass that closed every reachable call site; the PoC payload became the behavioural smoke test that proves the canonical attack stays inert as an argv element.","status":"published","published":"2026-06-19T15:12:58Z","modified":"2026-07-19T03:56:48.184958187Z","cvss":[{"version":"3.1","score":8.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high"}],"cwes":["CWE-78"],"updated_at":"2026-11-02T15:46:56.981655Z"}]}}