CriticalVulnerabilityLLM-specific

CVE-2026-61447: PraisonAI remote code execution in CodeAgent._execute_python()

Source: NVD(opens in a new tab)
Identifier: CVE-2026-61447
Published: July 11, 2026
Record updated: October 9, 2026

Affected: praisonaiagents <= 1.6.77
Fixed in: 1.6.78
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 2.5%

Summary

CVE-2026-61447 affects PraisonAI before 1.6.78. The CodeAgent._execute_python() function runs LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. An attacker who influences the model output through prompt injection can exfiltrate all environment secrets and execute arbitrary code on the host.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

CVSS score: 10(critical)
Patch available: Yes
CVSS vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
Attack vector: network
Attack complexity: low
Privileges required: none
User interaction: none
EPSS: 2.5%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on October 11, 2026.
Disclosure date: July 11, 2026

Weaknesses and techniques

Weakness (CWE): CWE-94
Attack pattern (CAPEC): CAPEC-242
AI threat technique (MITRE ATLAS): AML.T0051

Affected

Packages: praisonaiagents@<= 1.6.77 (fixed: 1.6.78)

Classification

Attack type: Prompt injection
Attack sophistication: Trivial
AI component targeted: Agent
Impact: Confidentiality,
Integrity,
Availability
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-61447

First tracked: July 11, 2026 at 02:07 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 95% (self-assessed)

Summary

Mitigation

Related items