Security Digest · Vulnerability record
CVE-2026-41497: PraisonAI has an incomplete fix for CVE-2026-34935 - OS Command Injection
PraisonAI is a multi-agent teams system. Prior to version 4.6.9, the fix for PraisonAI's MCP command handling does not add a command allowlist or argument validation to parsemcpcommand(), allowing arbitrary executables like bash, python, or /bin/sh with inline code execution flags to pass through to subprocess…
CVSS 9.8 Critical EPSS 0.8% · p55
Should you act?
Critical and remotely reachable
No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.
- Not in CISA KEV, but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
- EPSS 0.8%, percentile 55: FIRST’s model estimates a 0.8% chance of exploitation activity in the next 30 days, higher than 55% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Only applies if your dependency tree includes
praisonai(PyPI) <= 4.5.148, fixed in 4.5.149. Check your lockfile, including transitive dependencies.
What it is
PraisonAI is a multi-agent teams system. Prior to version 4.6.9, the fix for PraisonAI's MCP command handling does not add a command allowlist or argument validation to parsemcpcommand(), allowing arbitrary executables like bash, python, or /bin/sh with inline code execution flags to pass through to subprocess execution. This issue has been patched in version 4.6.9.
From the GitHub advisory
Summary
The fix for PraisonAI's MCP command handling does not add a command allowlist or argument validation to parsemcpcommand(), allowing arbitrary executables like bash, python, or /bin/sh with inline code execution flags to pass through to subprocess execution.
Affected Package
- Ecosystem: PyPI - Package: MervinPraison/PraisonAI - Affected versions: = 47bff65413be
Details
Weakness type: CWE-78, CWE-77.
Product: praisonai (PyPI) · Assigned by: GitHub_M · Published: 2026-05-08
Affected and fixed versions
| Ecosystem | Package | Vulnerable | First fixed |
|---|---|---|---|
| PyPI | praisonai | <= 4.5.148 | 4.5.149 |
| Vendor | Product | Affected versions (per CVE record) |
|---|---|---|
| MervinPraison | PraisonAI | < 4.6.9 |
Severity scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| GitHub_M | 3.1 | 9.8 Critical | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| GitHub | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
- Attack vector: network (remotely reachable)
- Attack complexity: low
- Privileges required: none (no login)
- User interaction: none
- Scope: unchanged
CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.
Exploitation and urgency
- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation poc, automatable yes, technical impact total.
- FIRST EPSS (model of 2026-10-21): 0.77% probability of exploitation activity in the next 30 days; percentile 55.
Timeline
- — GitHub-reviewed advisory GHSA-9qhq-v63v-fv3j published (critical)
- — CVE record last updated
- — CVE record published by GitHub_M
Sources and references
Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.
Vulnerability records
- GitHub Advisory GHSA-9qhq-v63v-fv3j github.com
- CVE.org record CVE-2026-41497 cve.org
- NVD entry CVE-2026-41497 nvd.nist.gov
Other references from the CVE record and advisory
- github.com github.com
- github.com github.com
- nvd.nist.gov nvd.nist.gov