Security Digest · Vulnerability record
CVE-2026-40088: PraisonAI Vulnerable to OS Command Injection
PraisonAI is a multi-agent teams system. Prior to 4.5.121, the executecommand function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbitrary shell commands through shell metacharacters.
CVSS 9.7 Critical EPSS 0.6% · p48
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 0.6%, percentile 48: FIRST’s model estimates a 0.6% chance of exploitation activity in the next 30 days, higher than 48% of all scored CVEs (low). EPSS is a probability, not a verdict.
- Needs a user to click or open something. Phishing makes that realistic, but it is not wormable.
- Only applies if your dependency tree includes
PraisonAI(PyPI) < 4.5.121, fixed in 4.5.121. Check your lockfile, including transitive dependencies.
What it is
PraisonAI is a multi-agent teams system. Prior to 4.5.121, the executecommand function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbitrary shell commands through shell metacharacters. This vulnerability is fixed in 4.5.121.
From the GitHub advisory
The executecommand function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbitrary shell commands through shell metacharacters.
---
Description
PraisonAI's workflow system and command execution tools pass user-controlled input directly to subprocess.run() with shell=True, enabling command injection attacks. Input sources include:
1. YAML workflow step definitions 2. Agent configuration files (agents.yaml) 3. LLM-generated tool call parameters 4. Recipe step configurations
Weakness type: CWE-78.
Product: PraisonAI (PyPI) · Assigned by: GitHub_M · Published: 2026-04-09
Affected and fixed versions
| Ecosystem | Package | Vulnerable | First fixed |
|---|---|---|---|
| PyPI | PraisonAI | < 4.5.121 | 4.5.121 |
| Vendor | Product | Affected versions (per CVE record) |
|---|---|---|
| MervinPraison | PraisonAI | < 4.5.121 |
Severity scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| GitHub_M | 3.1 | 9.7 Critical | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H |
| GitHub | 3.1 | 9.6 | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H |
- Attack vector: network (remotely reachable)
- Attack complexity: low
- Privileges required: none (no login)
- User interaction: required (a user must click/open something)
- Scope: changed (can affect other components)
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 no, technical impact total.
- FIRST EPSS (model of 2026-10-21): 0.60% probability of exploitation activity in the next 30 days; percentile 48.
Timeline
- — GitHub-reviewed advisory GHSA-2763-cj5r-c79m 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-2763-cj5r-c79m github.com
- CVE.org record CVE-2026-40088 cve.org
- NVD entry CVE-2026-40088 nvd.nist.gov
Other references from the CVE record and advisory
- github.com github.com
- github.com github.com