AI Threat AlertVibe-Trading LLM-callable tools permit command execution, code injection
PraisonAI Vulnerable to OS Command Injection
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
PraisonAI MCP `tools/call` path-traversal => RCE via Python `.pth` injection
husky/gpt_academic version <= 3.83, the plugin `CodeInterpreter` is vulnerable to code injection caused by prompt injection. The root cause is the execution of user-provided prompts that generate untrusted code
Flowise: Remote code execution vulnerability in AirtableAgent.ts caused by lack
enabled, channel metadata (topic/description) can be incorporated into the model's system prompt. Prompt injection is a documented risk for LLM-driven systems. This issue increases the injection surface
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
Prompt injection vulnerability in 1millionbot Millie chatbot that occurs when a user manages to evade chat restrictions using Boolean prompt injection techniques (formulating a question in such a way that
OpenClaude Sandbox Bypass via Model-Controlled `dangerouslyDisableSandbox` Input
JSONalyzeQueryEngine` in the run-llama/llama_index repository allows for SQL injection via prompt injection. This can lead to arbitrary file creation and Denial-of-Service (DoS) attacks. The vulnerability affects
GraphCypherQAChain class of langchain-ai/langchain version 0.2.5 allows for SQL injection through prompt injection. This vulnerability can lead to unauthorized data manipulation, data exfiltration, denial of service
server CORS wildcard + auth-off-by-default enables CSRF graph exfiltration and persistent indirect prompt injection
Flowise: APIChain Prompt Injection SSRF in GET/POST API Chains
Airtable Agent nodes that allows unauthenticated attackers to inject malicious code via prompt injection. Attackers can exploit unblocked pandas functions like pd.read_json() to exfiltrate datasets, perform SSRF against internal
langchain-ai/langchainjs versions 0.2.5 and all versions with this class allows for prompt injection, leading to SQL injection. This vulnerability permits unauthorized data manipulation, data exfiltration, denial of service
CodeWhale: Project config `instructions` override enables arbitrary file read into
PandasAI uses an interactive prompt function that is vulnerable to prompt injection and run arbitrary Python code that can lead to Remote Code Execution (RCE) instead of the intended explanation
DeepSeek TUI: run_tests Tool Enables RCE via Malicious Repository