Connect your agent
AdvisoriesCriticalCheck your lockfilePluginHow it worksPricing Connect your agent

Advisory record · GHSA-4p62-hqp5-g644

MCP-for-Stata: Command injection via log_file_name parameter in Stata command wrapper

CVSS 9.3 CriticalCriticalEPSS 0.0038 · 33rd percentile

Critical, because:

  • CVSS score 9.3: 9.0 or more.

How we decide what’s critical

Published by the GitHub Advisory Database at 29 Jun 2026, 11:50 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
stata-mcpPyPI<1.17.31.17.3
Identifiers
GHSA-4p62-hqp5-g644 · CVE-2026-47708 · PYSEC-2026-544
Weakness (CWE)
CWE-77
Tags
Published
29 Jun 2026
Updated
1 Jul 2026

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

Packages: stata-mcp versions before 1.17.3 are affected. The log_file_name parameter in the stata_do API and CLI is inserted into a Stata command string without validation, so an attacker who can call these interfaces can inject arbitrary Stata commands, including shell commands, and write files outside the log directory. Upgrade to stata-mcp 1.17.3 or later; the source gives no other workaround.

Written 10 Nov 2026.

Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

Severity and exploitation

ScoreRatingCVSSVectorSource
9.3 Critical 4.0 CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N CNA (GitHub_M)
  • CISA KEV Not listed.
  • EPSS 0.0038, the 33rd percentile, on 14 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

This record came from the full history of the GitHub Advisory Database, published 29 Jun 2026. New records show when each source confirmed them.

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.