VulnWatch VulnWatch
← Back to dashboard
#

Prompt Injection

231 entries

Every Prompt Injection entry VulnWatch has indexed, sorted by publication date.

Subscribe to this tag's RSS feed

High github

SearXNG MCP Server: Unbounded Response Body Read Bypasses URL Size Limit in `web_url_read`

## Unbounded Response Body Read Bypasses URL Size Limit in `web_url_read` ### Summary The `web_url_read` MCP tool in mcp-searxng enforces its 5 MiB response-size limit exclusively by inspecting the...

Prompt Injection Agentic / MCP prompt injection mcp server ai agent ai model
7.5
CVSS
4 months ago
Critical nvd

CVE-2026-12045: Read-only transaction bypass in the pgAdmin 4 AI Assistant allows an attacker who can influence database content that th

Read-only transaction bypass in the pgAdmin 4 AI Assistant allows an attacker who can influence database content that the assistant reads to execute arbitrary SQL with the privileges of the pgAdmin us...

9.4
CVSS
4 months ago
High github

[Eclipse Theia] Indirect Prompt Injection via Auto-Loaded Workspace Prompt Template Files in AI Chat

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...

Prompt Injection Agentic / MCP prompt injection indirect prompt ai agent claude
0.0
CVSS
4 months ago
Medium github

[Eclipse Theia] Data Exfiltration via Markdown Image Rendering in AI Chat

In Eclipse Theia versions prior to 1.71.0, the AI chat rendered Markdown image tags from AI responses, triggering HTTP requests to arbitrary external URLs without restriction. Combined with prompt inj...

Prompt Injection Agentic / MCP prompt injection ai agent claude
0.0
CVSS
4 months ago
High github

[Eclipse Theia] Indirect Prompt Injection via Adversarial Workspace File and Directory Names in AI Chat

In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its prompt context without distinguishing them from system instructions. An attacke...

Prompt Injection Agentic / MCP prompt injection indirect prompt adversarial ai agent claude
0.0
CVSS
4 months ago
High github

AgenticMail: Unauthenticated inbound mail triggers bypassPermissions resume of the operator's Claude Code session (bridge-wake)

## Summary Two inbound-mail handlers act on a privileged effect without verifying that the sender is the operator, while a sibling handler in the same repo does. The higher-impact one: any external em...

Prompt Injection Remote Code Execution Agentic / MCP prompt injection indirect prompt claude code agentic claude
0.0
CVSS
4 months ago
High nvd

CVE-2026-46580: In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/*.prompttemplate in a workspace were auto

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...

Prompt Injection Agentic / MCP prompt injection indirect prompt ai agent
8.4
CVSS
4 months ago
High nvd

CVE-2026-44688: In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its

In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its prompt context without distinguishing them from system instructions. An attacke...

Prompt Injection Agentic / MCP prompt injection indirect prompt adversarial ai agent
8.4
CVSS
4 months ago
Medium nvd

CVE-2026-22551: In Eclipse Theia versions prior to 1.71.0, the AI chat rendered Markdown image tags from AI responses, triggering HTTP r

In Eclipse Theia versions prior to 1.71.0, the AI chat rendered Markdown image tags from AI responses, triggering HTTP requests to arbitrary external URLs without restriction. Combined with prompt inj...

Prompt Injection Agentic / MCP prompt injection ai agent
6.7
CVSS
4 months ago
High github

PraisonAI: Server-Side Request Forgery (SSRF) in SearxNG / search_web tools via attacker-controlled searxng_url parameter

### Summary A Server-Side Request Forgery (SSRF) vulnerability in the SearxNG / `search_web` search tools allows an attacker to make the server perform requests to arbitrary internal endpoints and rea...

Prompt Injection SSRF prompt injection llm
8.8
CVSS
4 months ago
Critical github

npm PraisonAI AgentOS exposes unauthenticated agent listing and invocation

## Summary The published npm package `praisonai` ships a TypeScript `AgentOS` HTTP server that defaults to `host: "0.0.0.0"` and registers sensitive agent routes without any authentication or authori...

9.4
CVSS
4 months ago
High github

PraisonAI: Webhook signature verification skipped (fail-open) when secret unset, allowing forged inbound webhooks (WhatsApp & Linear bots)

The WhatsApp and Linear bot adapters verify the inbound webhook HMAC signature only when a secret is configured. When the secret environment variable is unset — the default on a fresh install and comm...

Prompt Injection prompt injection
8.6
CVSS
4 months ago
Critical nvd

CVE-2026-55743: The shell tool command allowlist in the SecurityPolicy of OpenHuman desktop agent through 0.54.0 (default Supervised sec

The shell tool command allowlist in the SecurityPolicy of OpenHuman desktop agent through 0.54.0 (default Supervised security policy) can be bypassed to execute arbitrary OS commands with the privileg...

Prompt Injection Remote Code Execution prompt injection indirect prompt llm
9.4
CVSS
5 months ago
Low github

Pi Agent: Potential XSS in HTML session exports via Markdown URL sanitization bypass

# Potential XSS in HTML session exports via Markdown URL handling Pi HTML exports render session Markdown into a static HTML file. Affected versions did not consistently reject unsafe Markdown link a...

Prompt Injection prompt injection
2.5
CVSS
5 months ago
Unknown rss_bleepingcomputer

US Gov asks Anthropic to ban 'foreign national' access to Fable, Mythos

The US government has ordered Anthropic to block all foreign nationals from accessing Fable 5 and Mythos 5, forcing the company to suspend both models worldwide. Anthropic is complying but disputes th...

Prompt Injection anthropic jailbreak
5 months ago
Unknown rss_securityweek

Anthropic Disputes Fable 5 AI Jailbreak

An AI hacker claims to have achieved a prompt-based jailbreak shortly after Fable 5’s launch, but Anthropic says it’s not a real jailbreak. The post Anthropic Disputes Fable 5 AI Jailbreak appeared fi...

Prompt Injection anthropic jailbreak
5 months ago
Unknown rss_thehackernews

New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration

OpenAI has begun rolling out a new Lockdown Mode to ChatGPT for eligible personal accounts to reduce the risk of data exfiltration arising from prompt injection attacks. The feature is primarily desi...

Prompt Injection prompt injection chatgpt openai
5 months ago
High github

praisonai-platform: Agent endpoints accept any agent_id without workspace ownership check, cross-workspace read/update/delete IDOR

## Summary **Type:** Insecure Direct Object Reference. The agent CRUD endpoints (`GET / PATCH / DELETE /workspaces/{workspace_id}/agents/{agent_id}`) gate access on `require_workspace_member(workspac...

Prompt Injection prompt injection llm
8.3
CVSS
5 months ago
Medium github

MCP Server Kubernetes: kubectl-generic flag injection enables Kubernetes bearer token exfiltration

### Summary The `kubectl_generic` tool in `mcp-server-kubernetes` passes user-supplied flags directly to kubectl without any allowlist, enabling a **privilege escalation attack** within Kubernetes env...

Prompt Injection Auth Bypass Agentic / MCP prompt injection indirect prompt mcp server anthropic ai agent claude
6.1
CVSS
5 months ago
Critical nvd

CVE-2026-25879: Langroid is a framework for building large-language-model-powered applications. Prior to version 0.63.0, SQLChatAgent ex

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.63.0, SQLChatAgent executes SQL produced by an LLM, which is influenceable by prompt injection. When...

9.8
CVSS
5 months ago
High github

PraisonAI has an Arbitrary File Write in Python API

# Bug Report: Arbitrary File Write in Python API ## Summary Hidden metadata in a webpage causes PraisonAI agents to write attacker-controlled content to arbitrary paths. `write_file` skips path vali...

Prompt Injection Remote Code Execution prompt injection deepseek openai llm
0.0
CVSS
5 months ago
Critical github

PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)

## Summary `execute_code()` in `praisonaiagents/tools/python_tools.py` (v1.6.37, subprocess sandbox mode) can be fully bypassed using `print.__self__` to retrieve the real Python `builtins` module, f...

Prompt Injection prompt injection
9.9
CVSS
5 months ago
High github

PraisonAI: Arbitrary code execution via unguarded `spec.loader.exec_module` in `agents_generator.py` - sibling of CVE-2026-44334

Arbitrary code execution via ungated spec.loader.exec_module in agents_generator.py (v4.6.32 chokepoint refactor bypass) Summary The v4.6.32 chokepoint refactor (which patched CVE-2026-44334 / GHSA-xc...

8.1
CVSS
5 months ago
Unknown rss_thehackernews

ChatGPhish Vulnerability Turns ChatGPT Web Summaries Into a Phishing Surface

Cybersecurity researchers have disclosed details of a vulnerability in OpenAI ChatGPT that leverages the artificial intelligence (AI) assistant's implicit trust in Markdown links and images to trigger...

Prompt Injection prompt injection chatgpt openai
5 months ago
Critical github

Langroid has Prompt to SQL Injection, Leading to RCE

# Security Vulnerability Report: Prompt to SQL Injection leading to RCE in latest Langroid ## Affected Scope langroid < 0.63.0 ## Vulnerability Description SQLChatAgent executes SQL produced by an...

Prompt Injection Remote Code Execution prompt injection deepseek openai llm
9.8
CVSS
5 months ago