CVE-2026-61427 · GHSA-hc5v-gxvj-58wh
PraisonAI: MCP HTTP-stream transport is unauthenticated by default, exposing tool enumeration and an unvalidated tool-call surface
- Risk score
- 65/100
- CVSS
- 7.3 v3.1
- Exploit chance (30 days)
- 0.4%
- Published
- 15 Jul 2026
Open in the live forecast Today's forecast
What to know
- What it is
- PraisonAI before 4.6.78 exposes the MCP HTTP-stream transport without authentication by default: the CLI --api-key option defaults to None, and the server only enforces Authorization/Bearer checks when an API key is configured. When an operator runs 'praisonai mcp serve --transport http-stream' without an API key, an …
- Affected
- praisonai (pip) <= 4.6.77
- Fix
- Upgrade praisonai to 4.6.78 or later.
- Exploitation
- Public proof of concept
Story map
At a glance
praisonai: Amber, patch this week. The AICoder UI component exposes write_to_file and execute_command tools to the LLM with no path validation and no command sanitization. An attacker can achieve arbitrary file write to any location on the filesystem (including /root/.ssh/authorized_keys, /etc/crontab) and arbitrary command execution through prompt inj…
The flaws
- CVE-2026-61427: PraisonAI: MCP HTTP-stream transport is unauthenticated by default, exposing tool enumeration and an unvalidated tool-call surface (CVSS 7.3 · EPSS 0%)
- CVE-2026-61445: PraisonAI: AICoder Arbitrary File Write and Command Execution via LLM Tool Calls (CVSS 9.9 · EPSS 1%)
- CVE-2026-61426: PraisonAI: AgentOS defaults to network-exposed no-auth mode, allowing unauthenticated agent invocation and instruction disclosure (CVSS 8.6 · EPSS 0%)
- CVE-2026-61435: PraisonAI: Call API localhost-only authentication bypass via spoofed Host header (CVSS 8.2 · EPSS 1%)
The fix
Upgrade praisonai: 4.6.78 or later on your release line
Who is exposed: praisonai (pip) <= 4.6.77
Where it stands
- Public proof of concept
Connects to
- Same weakness: Missing authentication (CWE-306). 281 other warnings in 30 days
Why it is Amber
- CVSS 7.3 high
- Public exploit or proof of concept referenced
- Remotely exploitable without logging in
- On your watchlist: PyPI
Affected packages
| Package | Ecosystem | Vulnerable | Fixed in |
|---|---|---|---|
| praisonai | pip | <= 4.6.77 | 4.6.78 |
References
- https://github.com/advisories/GHSA-hc5v-gxvj-58wh
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hc5v-gxvj-58wh
- https://nvd.nist.gov/vuln/detail/CVE-2026-61427
- https://nvd.nist.gov/vuln/detail/CVE-2026-62178
- https://www.vulncheck.com/advisories/praisonai-before-authentication-bypass-via-http-stream
- https://github.com/advisories/GHSA-hc5v-gxvj-58wh
Original description
PraisonAI before 4.6.78 exposes the MCP HTTP-stream transport without authentication by default: the CLI --api-key option defaults to None, and the server only enforces Authorization/Bearer checks when an API key is configured. When an operator runs 'praisonai mcp serve --transport http-stream' without an API key, an unauthenticated client (no Authorization header, and no Origin header, which is also permitted) can initialize a session, enumerate the available tools (tools/list), and invoke tools (tools/call). Additionally, the dispatcher forwards tool-call arguments to handlers without validating them against the advertised inputSchema. The server binds to 127.0.0.1 by default, so remote exploitation requires the operator to bind to a network-accessible address (e.g., --host 0.0.0.0).
Last activity 8 Oct 2026. Patch Forecast updates every hour.