PT-2026-59581

Summary read skill file in skill tools.py allows reading arbitrary files from the filesystem by accepting an unrestricted skill path parameter. Unlike file tools.read file which enforces workspace boundary confinement, and unlike run skill script which requires critical-level approval, read skill...

PT-2026-59540

Summary PraisonAI's direct-prompt CLI automatically expands @url: mentions in raw prompt text before agent execution begins. If a prompt contains @url:, the CLI calls MentionsParser.process.... The @url: handler then performs a direct urllib.request.urlopen request to the attacker-controlled URL...

PT-2026-59212

Description The LangSmith SDK's prompt pull methods pull prompt / pull prompt commit in Python, pullPrompt / pullPromptCommit in JS/TS fetch and deserialize prompt manifests from the LangSmith Hub. These manifests may contain serialized LangChain objects and model configuration that affect runtim...

PT-2026-59574

Summary PraisonAI's direct-prompt CLI automatically expands @url: mentions in raw prompt text before agent execution begins. If a prompt contains @url:, the CLI calls MentionsParser.process.... The @url: handler then performs a direct urllib.request.urlopen request to the attacker-controlled URL...

PT-2026-59237

Description The LangSmith SDK's prompt pull methods pull prompt / pull prompt commit in Python, pullPrompt / pullPromptCommit in JS/TS fetch and deserialize prompt manifests from the LangSmith Hub. These manifests may contain serialized LangChain objects and model configuration that affect runtim...

PT-2026-59167

Summary Graphiti versions before 0.28.2 contained a Cypher injection vulnerability in shared search-filter construction for non-Kuzu backends. Attacker-controlled label values supplied through SearchFilters.node labels were concatenated directly into Cypher label expressions without validation. I...

PT-2026-59236

Advisory Details Title: Sandbox Escape to Remote Code Execution via Incomplete eval Mitigation in TableChatAgent Description: Summary Langroid is vulnerable to a critical Sandbox Escape leading to Remote Code Execution RCE in its TableChatAgent and VectorStore capabilities. When these agents...

SingGuard-NSFA: Extensible Guardrails for Agentic AI Via Generative Reasoning and Real-Time Classification

We present nsfaguard, a guardrail framework for securing agentic AI systems against operational threats, such as prompt injection, sensitive information extraction, malicious code requests, dangerous tool misuse, and resource exhaustion. We first introduce the NSFA taxonomy, which organizes 185...

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...

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

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...