Connect your agent
AdvisoriesCriticalCheck your lockfilePluginHow it worksPricing Connect your agent

Advisory record · GHSA-q7m5-3jmv-vm48

PraisonAI: ContextGatherer include resolution permits absolute and traversal reads outside the workspace

CVSS 6.8 MediumEPSS 0.0037 · 31st percentile

Published by the GitHub Advisory Database at 8 Oct 2026, 17:58 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
praisonaiPyPI<4.6.784.6.78
Identifiers
GHSA-q7m5-3jmv-vm48 · CVE-2026-61431 · PYSEC-2026-4258
Weakness (CWE)
CWE-22 · CWE-200
Tags
Published
8 Oct 2026
Updated
15 Oct 2026

Machine-written summary

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

PraisonAI versions before 4.6.78 (PyPI package praisonai) let ContextGatherer read files outside the configured workspace, because include entries in project-controlled .praisoncontext and .praisoninclude files can be absolute paths or ".." traversal paths. An attacker who can supply or modify a workspace repository and get context gathering run on it can expose process-readable files outside the project root, which are then added to the context bundle. Upgrade to praisonai 4.6.78 or later, which fixes the issue.

Written 1 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
6.8 Medium 4.0 CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N CNA (VulnCheck)
  • CISA KEV Not listed.
  • EPSS 0.0037, the 31st percentile, on 7 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

  1. 31 Oct 2026, 14:08 UTC First seen by agentprime
  2. 31 Oct 2026, 14:08 UTC Confirmed by OSV

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.