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 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...

EUVD-2026-43182

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...

EUVD-2026-43181

PraisonAI before 4.6.78 contains arbitrary file write and command execution vulnerabilities in the AICoder component due to missing path validation and command sanitization in LLM tool calls. Attackers can inject malicious prompts through the chat interface to write files to arbitrary filesystem...

EUVD-2026-43179

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

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 employing Abstract Syntax Tree AST...

CVE-2026-60086

PraisonAI before 4.6.78 contains a prompt injection defense bypass vulnerability where the injection defense only blocks threats classified as CRITICAL, requiring three or more detector families to match simultaneously. Attackers can craft single or double-vector prompt injections that are...

CVE-2026-60086

PraisonAI before 4.6.78 contains a prompt injection defense bypass. The defense only blocks threats classified as CRITICAL and requires three or more detector families to match. Attackers can craft single- or double-vector prompt injections rated HIGH that pass through unblocked to reach the mode...

EUVD-2026-42894

PraisonAI before 4.6.78 contains a prompt injection defense bypass vulnerability where the injection defense only blocks threats classified as CRITICAL, requiring three or more detector families to match simultaneously. Attackers can craft single or double-vector prompt injections that are...

CVE-2026-55615

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.5, Neo4jChatAgent passes LLM-generated Cypher queries straight to the Neo4j driver with no validation, no statement-type allowlist, and no opt-out gate. The query text is influenceable by prompt...

CVE-2026-50180

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.64.0, SQLChatAgent in langroid ships a validatequery defense-in-depth layer whose DANGEROUSSQLPATTERNS regex blocklist enumerates dangerous SQL primitives by specific function name. The list misses...

CVE-2026-55615

Langroid CVE-2026-55615 affects the Neo4jChatAgent path, where LLM-generated Cypher queries are sent unvalidated to the Neo4j driver prior to version 0.65.5. Connected docs describe a prompt-injection risk enabling read/write/destroy of graph data and, with APOC or dbms.security, potential OS com...

CVE-2026-55615

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.5, Neo4jChatAgent passes LLM-generated Cypher queries straight to the Neo4j driver with no validation, no statement-type allowlist, and no opt-out gate. The query text is influenceable by prompt...

CVE-2026-55615 Langroid: Neo4jChatAgent executes LLM-generated Cypher without validation (prompt-to-Cypher injection; config-conditional RCE), mirroring the SQLChatAgent bug fixed in CVE-2026-25879

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.5, Neo4jChatAgent passes LLM-generated Cypher queries straight to the Neo4j driver with no validation, no statement-type allowlist, and no opt-out gate. The query text is influenceable by prompt...

CVE-2026-59807

CVE-2026-59807 affects Composio SDK prior to 0.2.32-beta.283. A path validation bypass in readFileFromDisk (tool-file-uploads.ts) can enable an attacker to read and exfiltrate sensitive files by manipulating file_uploadable parameters via prompt injection, referencing sensitive paths such as SSH ...

CVE-2026-59807 Composio SDK < 0.2.32-beta.283 - Sensitive File Upload via tool-file-uploads.ts

Composio SDK before 0.2.32-beta.283 contains a path validation bypass vulnerability that allows attackers to read and exfiltrate sensitive files by exploiting a missing assertSafeFileUploadPath check in the readFileFromDisk function within tool-file-uploads.ts. Attackers can exploit prompt...

New HalluSquatting Attack Could Trick AI Coding Assistants Into Installing Botnet Malware

AI coding assistants have a habit of making things up. Ask one to fetch a popular tool, and it will sometimes hand back a real-sounding name for a project that does not exist. New research, which its authors call HalluSquatting , turns that habit into an attack: work out the fake names an AI...