CVE-2026-56838: Command Injection (CVSS 7.8)

Description

PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.59, PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes allow_dangerous_tools=True. The normal recipe.run() path enforces this with _check_tool_policy(). The streaming path, recipe.run_stream(), loads the same recipe, checks dependencies, and then calls _execute_recipe() without running the dangerous-tool policy check. As a result, a recipe that honestly declares execute_command in TEMPLATE.yaml requires.tools is denied by recipe.run(), but reaches the execution engine through recipe.run_stream() with allow_dangerous_tools=False. This issue has been patched in version 4.6.59.

Is your site exposed to CVE-2026-56838?

Run a free security scan — no signup, results in seconds.

CVSS v3.1 Score

7.8

HIGH

CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

EPSS — Exploit Prediction

0.0015

Probability of exploitation

0.04%

Percentile rank

EPSS estimates the probability that this vulnerability will be exploited in the wild within the next 30 days. A higher score means more likely to be exploited.

Weakness Type (CWE)

CWE-78 OS Command Injection

CWE-693 CWE-693

CWE-863 Incorrect Authorization

References

Other References

https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-v847-hxxw-3pxg https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-v847-hxxw-3pxg

Frequently Asked Questions

What is CVE-2026-56838? +

PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.59, PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes allow_dangerous_tools=True. The normal recipe.run() path enforces this with _check_tool_policy(). The streaming path, recipe.run_stream(), loads the same recipe, checks dependencies, and then calls _execute_recipe() without running the dangerous-tool policy check. As a result, a recipe that honestly declares execute_command in TEMPLATE.yaml requires.tools is denied by recipe.run(), but reaches the execution engine through recipe.run_stream() with allow_dangerous_tools=False. This issue has been patched in version 4.6.59. It has a CVSS v3.1 base score of 7.8 (HIGH).

How severe is CVE-2026-56838? +

CVE-2026-56838 has a CVSS v3.1 score of 7.8 out of 10, rated HIGH. This is a high-severity vulnerability that should be prioritized for patching. The EPSS score is 0.0015, placing it in the 0th percentile for exploitation probability.

How do I check if I'm vulnerable to CVE-2026-56838? +

You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

Related Vulnerabilities

CVE-2024-54012

Penetration Testing engineers at Amazon discovered a vulnerability where the camera system failed to properly validate input, allowing specially crafted …

CVE-2026-8652

An OS Command Injection vulnerability exists in Aterm. If a malicious third person gains administrator access to the product’s web …

CVE-2025-13605

3onedata modbus gateway device model GW1101-1D(RS-485)-TB-P (hardware version V2.2.0) allows authenticated users to execute arbitrary shell commands in the context …

CVE-2026-41925

WDR201A WiFi Extender (HW V2.1, FW LFMZX28040922V1.02) contains an OS command injection vulnerability in the adm.cgi binary's reboot_time function that …

CVE-2026-41924

WDR201A WiFi Extender (HW V2.1, FW LFMZX28040922V1.02) contains an OS command injection vulnerability in the makeRequest.cgi binary that allows unauthenticated …

CVE-2026-41923

WDR201A WiFi Extender (HW V2.1, FW LFMZX28040922V1.02) contains an OS command injection vulnerability in the internet.cgi binary that allows unauthenticated …