Patch Forecast
Amber warning
Patch this week.

CVE-2026-61436 · GHSA-7c92-x8vg-4258

PraisonAI: AgentMail webhook mode accepts forged unsigned message.received events and invokes agents

Risk score
66/100
CVSS
8.6 v3.1
Exploit chance (30 days)
0.3%
Published
15 Jul 2026

Open in the live forecast Today's forecast

What to know

What it is
PraisonAI before 4.6.78 fails to verify Svix webhook signatures in AgentMail webhook mode, allowing unauthenticated attackers to forge message.received events. Attackers can send crafted JSON payloads to the webhook endpoint to invoke configured agents with arbitrary sender addresses and message content.
Affected
praisonai (pip) <= 4.6.77
Fix
Upgrade praisonai to 4.6.78 or later.
Exploitation
No known exploitation

Story map

Story map: praisonaiTHE FLAWSTHE FIXCVE-2026-61436PraisonAI: AgentMail webhookmode accepts forged unsignedmessage.received events and…CVSS 8.6 · EPSS 0%CVE-2026-61445PraisonAI: AICoder ArbitraryFile Write and CommandExecution via LLM Tool CallsCVSS 9.9 · EPSS 1%CVE-2026-61426PraisonAI: AgentOS defaults tonetwork-exposed no-authmode, allowing…CVSS 8.6 · EPSS 0%CVE-2026-61435PraisonAI: Call APIlocalhost-only authenticationbypass via spoofed Host headerCVSS 8.2 · EPSS 1%Upgrade praisonai4.6.78or later on your release lineWho is exposedpraisonai (pip) <= 4.6.77AMBER · PATCH THIS WEEKpraisonaiThe AICoder UI componentexposes write_to_file andexecute_command tools to theLLM with no path validation andno command sanitization. Anattacker can achieve arbitraryfile write to any location on…Where it standsPublic proof of conceptCONNECTS TOSame weaknessAuthentication bypass (CWE-287)236 other warnings in 30 days →
Story map: the flaws, the fix, how it unfolded and what it connects to. Boxes link to the record or article.

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-2026-61436: PraisonAI: AgentMail webhook mode accepts forged unsigned message.received events and invokes agents (CVSS 8.6 · 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

Why it is Amber

  • CVSS 8.6 high
  • Remotely exploitable without logging in
  • On your watchlist: PyPI

Affected packages

PackageEcosystemVulnerableFixed in
praisonaipip<= 4.6.774.6.78

References

Original description

PraisonAI before 4.6.78 fails to verify Svix webhook signatures in AgentMail webhook mode, allowing unauthenticated attackers to forge message.received events. Attackers can send crafted JSON payloads to the webhook endpoint to invoke configured agents with arbitrary sender addresses and message content.

Last activity 7 Oct 2026. Patch Forecast updates every hour.