PraisonAI: Protection Mechanism Failure
CVE-2026-57137 is a high-severity protection mechanism failure vulnerability in PraisonAI from MervinPraison, with a CVSS 3.1 base score of 8.8 out of 10. It can be exploited remotely over the network by an attacker with a low-privileged account, without any action from a user. Affected PraisonAI versions: >= 1.4.0, < 1.7.2. The record does not name a fixed version, so check the vendor advisory. There is no confirmed exploitation so far. EPSS estimates a 0.51% chance of exploitation within 30 days, which is low compared with other CVEs.
High severity with no evidence of exploitation so far.
What to do
- Check which version of PraisonAI you run against the affected versions below, and install the vendor's latest release.
- Read the advisory on github.com for workarounds and exact fixed builds.
Affected products and versions
| Vendor | Product | Affected versions | Fixed in |
|---|---|---|---|
| MervinPraison | PraisonAI | >= 1.4.0, < 1.7.2 | Not stated |
Version data comes from the organisation that assigned the CVE. Confirm against the vendor advisory before deciding you are unaffected.
How the severity score breaks down
- Attack vector
- NetworkCan be exploited remotely over a network, including the internet.
- Attack complexity
- LowNo special conditions are needed; the attack works reliably.
- Privileges required
- LowA basic user account is enough.
- User interaction
- NoneNo action by a victim is required.
- Scope
- UnchangedImpact stays within the vulnerable component.
- Confidentiality
- HighAll data handled by the component can be read.
- Integrity
- HighData or code can be modified at will.
- Availability
- HighThe component can be taken down completely.
Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H. Scored by CNA (github.com).
Official description
PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText() before invoking the onToolCall approval callback. Because the wrapped AI SDK executes tool handlers during generation, a callback that returns false records tool_rejected only after the denied tool has already produced side effects and populated toolResults. Applications using onToolCall as a human or policy approval boundary can therefore execute rejected file, command, API, or data-modifying operations. This issue is fixed in version 1.7.2.
Source: the CVE record as published by its numbering authority, via NVD and CVE.org.
The underlying weakness: Protection Mechanism Failure
The product does not use or incorrectly uses a protection mechanism that provides sufficient defense against directed attacks against the product.
Timeline
- CVE record published.
- CISA published its SSVC assessment (exploitation: poc, automatable: no, technical impact: total).
References
Patches and release notes
Other vulnerabilities in PraisonAI
- 7.5 High severity
- 8.8 High severity
- 7.8 High severity
- 8.1 High severity
- 8.8 High severity
- 9.8 Critical severity
Recent Protection Mechanism Failure vulnerabilities
- 7.8 High severity
- 7.8 High severity
- 8.4 High severity
- 7.8 High severity
- 8.4 High severity
- 8.4 High severity
Spotted an error? Tell us.