CVE-2026-58195 json
Agentic-Flow: OS Command Injection in agentic-flow MCP server tools via unsanitized tool-parameter interpolation into execSync
published 4mo ago modified 18d ago also GHSA-vcv2-r9jh-99m5 , EUVD-2026-45256
- cvss
- 8.8
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.6%
- EPSS 0.6% chance of exploitation in 30 days, percentile 47%
- public exploits
- 0
- none known
Summary
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.
Patch / fix
- npm agentic-flow 2.0.14
- github.com/ruvnet/agentic-flow@0c2ec96 commit
- github.com/ruvnet/agentic-flow#170 pull request
- github.com/ruvnet/ruflo#2415 pull request
- github.com/ruvnet/ruflo/releases/tag/v3.12.4 release
Is CVE-2026-58195 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.
Check with FencerCISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- no
- Technical impact
- total
- Assessed
- 3mo ago
Exploit prediction
0.56% chance of exploitation in the next 30 days, higher than 47% of all scored CVEs (FIRST EPSS, 2026-11-11).
Exploits and checks
- github.com https://github.com/ruvnet/agentic-flow/security/advisories/GHSA-vcv2-r9jh-99m5 referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 8.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
| GitHub | 3.1 | 8.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| npm | agentic-flow | <2.0.14 |
2.0.14 |
Affected products
- ruvnet agentic-flow
Classification
- Weakness
-
- CWE-78 Improper Neutralization of Special Elements used in an OS Command
References
-
github.com
/ruvnet/agentic-flow/pull/170
web
-
github.com
/ruvnet/ruflo/pull/2415
web
- github.com /ruvnet/agentic-flow/commit/0c2ec967736a8b6b85832c6bae2a3e74989705ec
-
github.com
/ruvnet/agentic-flow/security/advisories/GHSA-vcv2-r9jh-99m5
exploit, web
-
github.com
/ruvnet/agentic-flow/issues/169
web
-
github.com
/ruvnet/ruflo/issues/2414
web
-
github.com
/ruvnet/ruflo/releases/tag/v3.12.4
web
-
github.com
/ruvnet/agentic-flow
package
-
npmjs.com
/package/agentic-flow/v/2.0.14
web
Sources
- CVE List CVE-2026-58195
- GitHub Advisory GHSA-vcv2-r9jh-99m5
- NVD CVE-2026-58195
Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.