UTC
Critical

PraisonAI: AgentOS remains unauthenticated after incomplete fix version and allows remote agent invocation

CVE-2026-57116 · GHSA-892r-p3jq-jp24 · published 2026-06-18 · updated 2026-07-20

Severity
Critical
CVSS score
9.8
Chance of exploitation (EPSS)
0.42%
Fixed in
4.6.59
  • Exploitation Public proof of concept
  • Automatable Yes
  • Technical impact Total
  • CISA SSVC
What it is

If an operator exposes an AgentOS app on a reachable interface, any client that can reach it can: enumerate deployed agents through GET /api/agents; read agent names, roles, and instruction snippets; invoke the default agent or a named agent through POST /api/chat; trigger downstream tools, private context reads, memory accesses, API integrations, browser actions, or other side effects attached to the agent; consume model/API budget through repeated invocation. The exact downstream impact depends on the deployed agents. The framework-level boundary failure is that a production deployment surface exposes agent control without authentication and defaults to binding on all interfaces.

What to do

Upgrade praisonai to 4.6.59 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

This report is related to GHSA-pm96-6xpr-978x / CVE-2026-40151. The published advisory describes AgentOS instruction disclosure and lists 4.5.128 as patched. It also mentions unauthenticated /api/chat as a chained instruction-extraction path. The current report should be treated as an incomplete fix / affected-range correction with a broader demonstrated impact: the published patched version v4.5.128 still reproduces; latest release v4.6.57 still reproduces; current main still reproduces; the PoV proves unauthorized agent invocation and side effects, not only instruction disclosure.

Affected
PackageRegistryAffectedFixed in
praisonaiPyPI>= 4.2.1, <= 4.6.574.6.59

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].