Unsafe Dependency Resolution

Overview @theia/ai-editor is a Theia - AI Editor Affected versions of this package are vulnerable to Unsafe Dependency Resolution via the automatic loading of .prompts/.prompttemplate files in a workspace. An attacker can manipulate the AI agent's system instructions by introducing crafted prompt...

Unsafe Dependency Resolution

Overview @theia/ai-chat is a Theia - AI Chat Extension Affected versions of this package are vulnerable to Unsafe Dependency Resolution via the automatic loading of .prompts/.prompttemplate files in a workspace. An attacker can manipulate the AI agent's system instructions by introducing crafted...

CVE-2026-46580

In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/.prompttemplate in a workspace were automatically loaded and could override or extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the...

CVE-2026-46580

In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/.prompttemplate in a workspace were automatically loaded and could override or extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the...

CVE-2026-46580

Theia before v1.71.0 loads files matching .prompts/*.prompttemplate from a workspace, allowing attacker-controlled content to override the AI agent’s system prompts (indirect prompt injection). This enables attack chains with untrusted workspaces, potentially causing data exfiltration via Markdow...

EUVD-2026-37899

In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/.prompttemplate in a workspace were automatically loaded and could override or extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the...

npm PraisonAI MCPServer exposes unauthenticated HTTP tools/call

Summary The published npm package praisonai exports a TypeScript MCPServer that can expose tools, resources, and prompts over an HTTP JSON-RPC transport with: ts await server.start port: 3000 ; The HTTP transport has no authentication or authorization path. MCPServerConfig does not expose an...

GHSA-J4F3-55X4-R6Q2 npm PraisonAI MCPServer exposes unauthenticated HTTP tools/call

Summary The published npm package praisonai exports a TypeScript MCPServer that can expose tools, resources, and prompts over an HTTP JSON-RPC transport with: ts await server.start port: 3000 ; The HTTP transport has no authentication or authorization path. MCPServerConfig does not expose an...

GHSA-C969-5X3P-VQ3V PraisonAI: IMAP Command Injection via Unsanitized Email Search Parameters

Summary The email search tool in src/praisonai-agents/praisonaiagents/tools/emailtools.py constructs IMAP SEARCH commands by interpolating LLM-controlled parameters fromaddr, subject, query directly into IMAP protocol strings using f-string formatting with double-quote delimiters. An attacker who...

PraisonAI: IMAP Command Injection via Unsanitized Email Search Parameters

Summary The email search tool in src/praisonai-agents/praisonaiagents/tools/emailtools.py constructs IMAP SEARCH commands by interpolating LLM-controlled parameters fromaddr, subject, query directly into IMAP protocol strings using f-string formatting with double-quote delimiters. An attacker who...

CVE-2026-56077: Exposure of Resource to Wrong Sphere

PraisonAI before 1.5.115 contains an information disclosure vulnerability in the MultiAgentLedger component that allows attackers to access sensitive data by registering agents with duplicate IDs. Attackers can exploit the lack of agent ID uniqueness enforcement to share ledger instances and expo...

CVE-2026-46580: Inclusion of Functionality from Untrusted Control Sphere

In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/.prompttemplate in a workspace were automatically loaded and could override or extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the...

PT-2026-50691

Name of the Vulnerable Software and Affected Versions Eclipse Theia versions prior to 1.71.0 Description Files matching the pattern .prompts/.prompttemplate in a workspace are automatically loaded, allowing them to override or extend the AI agent's system prompts. This enables indirect prompt...

PT-2026-50808

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 1.5.115 Description An information disclosure issue exists in the MultiAgentLedger component. The system fails to enforce the uniqueness of agent IDs, allowing attackers to register agents with duplicate IDs. This...

PT-2026-50481

Name of the Vulnerable Software and Affected Versions Open-webui affected versions not specified Description An authenticated user can access files belonging to other users by exploiting a lack of ownership verification in the image processing path. When the POST endpoint "/api/chat/completions"...

LiteLLM Vulnerability Chain Lets Low-Privilege Users Take Over AI Gateway Servers

A default low-privilege account on a LiteLLM proxy can climb to full admin and run code on the server by chaining three vulnerabilities, researchers at Obsidian Security disclosed LiteLLM is a widely deployed open-source AI gateway that brokers calls to more than 100 model providers behind one...

EUVD-2026-36614

OpenClaw before 2026.4.26 contains an information disclosure vulnerability in sandboxed session spawning that exposes the real workspace path to child prompts. Attackers can exploit this by spawning child sessions from sandboxed parents to reveal host workspace location or related memory context ...

CVE-2026-53826

OpenClaw before 2026.4.26 contains an information disclosure vulnerability in sandboxed session spawning that exposes the real workspace path to child prompts. Attackers can exploit this by spawning child sessions from sandboxed parents to reveal host workspace location or related memory context ...

CVE-2026-53826 OpenClaw < 2026.4.26 - Information Disclosure via Sandboxed Session Spawn

OpenClaw before 2026.4.26 contains an information disclosure vulnerability in sandboxed session spawning that exposes the real workspace path to child prompts. Attackers can exploit this by spawning child sessions from sandboxed parents to reveal host workspace location or related memory context ...

CVE-2026-44785 Discourse: Hidden reply-to post raw can be disclosed through AI explain prompts

Discourse is an open-source discussion platform. From versions 2026.1.0-latest to before 2026.1.4, 2026.3.0-latest to before 2026.3.1, and 2026.4.0-latest to before 2026.4.1, the AI "explain" helper only checks cansee? on the post being explained, not its replytopost, so any authenticated user wi...