GHSA-5R2Q-3WG3-57M2 Duplicate Advisory: PraisonAI: Prompt Injection Defense Bypassed for HIGH-Level Threats

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-fj8f-m44g-c479. This link is maintained to preserve external references. Original Description PraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the block threshold defaul...

Insecure Default Initialization of Resource

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

CVE-2026-61447

PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent.executepython that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment...

CVE-2026-61439

PraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the block threshold defaults to CRITICAL severity, allowing HIGH-level threats to pass through unblocked. Attackers can submit single-vector prompt injection attacks such as instruction overrides or financi...

CVE-2026-61447

PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent.executepython that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment...

CVE-2026-61447 PraisonAI before 1.6.78 Remote Code Execution via CodeAgent

PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent.executepython that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment...

CVE-2026-61447 PraisonAI before 1.6.78 Remote Code Execution via CodeAgent

PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent.executepython that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment...

CVE-2026-61447

PraxionAI before 1.6.78 exposes a remote code execution flaw in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandboxing. This enables prompt-injection to exfiltrate environment secrets and run arbitrary code on the host. The v...

CVE-2026-61445

Summary (CVE-2026-61445) PraisonAI prior to 4.6.78 exposes arbitrary file write and command execution via the AICoder component. The root cause is missing path validation and lack of command sanitization in LLM tool calls, enabling an attacker to inject malicious prompts through the chat interfac...

CVE-2026-61439 PraisonAI before 4.6.78 Prompt Injection Defense Bypass

PraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the block threshold defaults to CRITICAL severity, allowing HIGH-level threats to pass through unblocked. Attackers can submit single-vector prompt injection attacks such as instruction overrides or financi...

CVE-2026-61439

Summary: CVE-2026-61439 affects PraisonAI

CVE-2026-61439 PraisonAI before 4.6.78 Prompt Injection Defense Bypass

PraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the block threshold defaults to CRITICAL severity, allowing HIGH-level threats to pass through unblocked. Attackers can submit single-vector prompt injection attacks such as instruction overrides or financi...

Command Injection

langroid is vulnerable to Command Injection. The vulnerability is due to the Neo4jChatAgent executing LLM-generated Cypher queries without validation, statement-type restrictions, or an opt-out mechanism, which allows an attacker to exploit prompt injection to execute arbitrary Cypher queries,...

Weekly Metasploit Update: Exploits for FlowiseAI CSV Agent and MacOS Package Kit

More AI, more software, more bugs! AI, it's all you hear about nowadays and everyone's got an opinion on it. Here at Metasploit, we care less about those opinions and more about the growing attack surface all this new software brings with it yeehaw exploits!. Take for example the new Flowise CSV...

PT-2026-57440

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 1.6.78 Description A remote code execution issue exists in the CodeAgent. execute python function. The software executes Python code generated by a Large Language Model LLM without Abstract Syntax Tree AST validatio...

CVE-2026-61439: Initialization of a Resource with an Insecure Default

PraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the block threshold defaults to CRITICAL severity, allowing HIGH-level threats to pass through unblocked. Attackers can submit single-vector prompt injection attacks such as instruction overrides or financi...

CVE-2026-61447: Improper Control of Generation of Code

PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent.executepython that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment...

PT-2026-57437

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 4.6.78 Description A prompt injection defense misconfiguration exists where the block threshold defaults to CRITICAL severity. This allows threats categorized as HIGH severity to pass through without being blocked...

PT-2026-57439

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 4.6.78 Description The AICoder component contains flaws allowing arbitrary file write and command execution. These issues result from missing path validation and inadequate command sanitization during Large Language...

mcp-atlassian: Arbitrary file read via missing path validation in confluence_upload_attachment

Summary confluenceuploadattachment passes filepath directly to openfilepath, "rb" with no path validation. Any authenticated MCP client — or an AI agent manipulated via prompt injection — can read any file the server process can access and exfiltrate it to Confluence as an attachment. Details Roo...