https://vulnerability.circl.lu/rss/recent/all/10 Most recent entries from all 2026-10-04T18:37:59.635790+00:00 Vulnerability-Lookup info@circl.lu python-feedgen Contains only the most 10 recent entries. https://vulnerability.circl.lu/vuln/fkie_cve-2026-58195 fkie_cve-2026-58195 2026-10-04T18:37:59.637928+00:00

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.

 https://vulnerability.circl.lu/vuln/ghsa-vcv2-r9jh-99m5 GHSA-vcv2-r9jh-99m5 — Agentic-Flow: OS Command Injection in agentic-flow MCP server tools via unsanitized tool-parameter interpolation into e… 2026-10-04T18:37:59.638011+00:00

Affected: npm: agentic-flow

## Summary

`agentic-flow` versions `<= 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.

This was a partial-fix gap: prior commit `6a06854` (#158) fixed CWE-78 elsewhere in the project but missed the MCP server files entirely.

## Impact

Any 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.

## Affected components

- `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_b…