Vulnerability · Published Oct 23, 2026 · Assigned by GitHub_M
CVE-2026-57116PraisonAI: AgentOS remains unauthenticated after GHSA-pm96 patched version and allows remote agent invocation
Critical 9.8
In plain English
A critical-severity information exposure in PraisonAI from MervinPraison. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 36% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official description
PraisonAI is a multi-agent teams system. From version 4.2.1 to before version 4.6.59, PraisonAI's AgentOS FastAPI deployment surface remains unauthenticated in current main and in releases after the published patched version for GHSA-pm96-6xpr-978x / CVE-2026-40151. The chat route directly calls agent.chat(request.message). No-auth and wrong-bearer requests both execute the deployed agent. This is broader than passive metadata disclosure. In any deployment where AgentOS wraps agents with tools, private context, memory, API integrations, or cost-bearing model calls, an unauthenticated reachable client can drive those agents. This issue has been patched in version 4.6.59.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | praisonai | 4.6.59 | GHSA-892r-p3jq-jp24 |
| PyPI | praisonai | 4.6.59 | PYSEC-2026-3507 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| MervinPraison | PraisonAI | >= 4.2.1, < 4.6.59 |
Weakness: CWE-200, CWE-306, CWE-862 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H