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

Critical nvd

CVE-2026-17351: The fix for CVE-2026-12045 in pgAdmin 4 9.16 required the LLM-supplied query passed to the AI Assistant's execute_sql_qu

The fix for CVE-2026-12045 in pgAdmin 4 9.16 required the LLM-supplied query passed to the AI Assistant's execute_sql_query tool to parse, via sqlparse, as exactly one non-transaction-control statemen...

9.4
CVSS
3 months ago
Medium github

@dynatrace-oss/dynatrace-mcp-server has a workflow template injection via create_workflow_for_notification

### Summary A template injection vulnerability in the `create_workflow_for_notification` tool lets a caller embed Jinja2 expressions that the Dynatrace workflow engine evaluates at runtime, exfiltrati...

4.2
CVSS
3 months ago
Medium github

@dynatrace-oss/dynatrace-mcp-server has a DQL injection via parameters not documented as DQL

### Summary A DQL injection vulnerability in several read tools lets a caller bypass the tools' documented field-scope, time-window, and display caps by injecting DQL pipeline stages through parameter...

4.3
CVSS
3 months ago
Medium nvd

CVE-2026-17534: Kimi Code (@moonshot-ai/kimi-code) before 0.27.0 implements FetchURL SSRF hardening as a static hostname and IP-literal

Kimi Code (@moonshot-ai/kimi-code) before 0.27.0 implements FetchURL SSRF hardening as a static hostname and IP-literal denylist in assertSafeFetchTarget, without resolving DNS or re-validating hosts...

Prompt Injection SSRF prompt injection
5.5
CVSS
3 months ago
High github

Claude Code: Sandbox Escape via Git Worktree Path Confusion Allows Unsandboxed Code Execution

Claude Code's worktree handling allowed creation of worktrees named ".git" and navigation to worktrees outside the sandbox context, enabling git directory confusion attacks. By exploiting symlink mani...

Prompt Injection prompt injection claude code anthropic claude
0.0
CVSS
3 months ago
Medium github

BlenderMCP path traversal in download_polyhaven_asset allows arbitrary file writes

BlenderMCP before commit 30a3308 contains a path traversal vulnerability in the download_polyhaven_asset method that allows attackers to write arbitrary files by injecting traversal sequences in API r...

Prompt Injection prompt injection
5.3
CVSS
3 months ago
Medium nvd

CVE-2026-66004: BlenderMCP before commit 30a3308 contains a path traversal vulnerability in the download_polyhaven_asset method that all

BlenderMCP before commit 30a3308 contains a path traversal vulnerability in the download_polyhaven_asset method that allows attackers to write arbitrary files by injecting traversal sequences in API r...

Prompt Injection prompt injection
6.0
CVSS
3 months ago
Unknown rss_thehackernews

ThreatsDay: Android Spyware, PLC Attacks, AI Image Prompt Injection + 12 More Stories

Most of this week's trouble came dressed as something useful. A package stole data. A fake extension opened remote access. A safety app became spyware. An image gave hidden orders to an AI agent. Oth...

Prompt Injection Agentic / MCP prompt injection ai agent
3 months ago
Medium nvd

CVE-2026-44192: A flaw was found in the Ansible Lightspeed Model Context Protocol (MCP) server. This vulnerability, known as path traver

A flaw was found in the Ansible Lightspeed Model Context Protocol (MCP) server. This vulnerability, known as path traversal, allows an attacker to manipulate an AI agent through indirect prompt inject...

Prompt Injection Agentic / MCP model context protocol prompt injection indirect prompt ai agent
6.6
CVSS
3 months ago
High nvd

CVE-2026-65056: mcp-webresearch 0.1.7 contains a server-side request forgery vulnerability that allows attackers to access internal netw

mcp-webresearch 0.1.7 contains a server-side request forgery vulnerability that allows attackers to access internal network services by supplying loopback, link-local, or cloud metadata addresses to t...

Prompt Injection SSRF prompt injection llm
8.3
CVSS
3 months ago
High nvd

CVE-2026-57495: AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/claudecode prior to version 0.2.39,

AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/claudecode prior to version 0.2.39, @agenticmail/codex prior to version 0.1.33, @agenticmail/core prior to version 0...

Prompt Injection Agentic / MCP prompt injection indirect prompt claude code ai agent agentic claude
8.2
CVSS
3 months ago
Unknown rss_thehackernews

OpenAI’s GPT-Red Automates Prompt Injection Testing to Harden GPT-5.6 Sol

OpenAI has disclosed details of GPT-Red, an internal automated red-teaming model that scales prompt injection vulnerability discovery with an aim to fix issues before the tools are deployed widely. "...

Prompt Injection prompt injection adversarial openai gpt-5
4 months ago
Medium nvd

CVE-2026-11371: The BetterDocs WordPress plugin before 4.5.5 does not sanitise an AI-generated documentation summary before storing and

The BetterDocs WordPress plugin before 4.5.5 does not sanitise an AI-generated documentation summary before storing and outputting it, and the feature that generates it is exposed to unauthenticated...

Prompt Injection prompt injection
6.1
CVSS
4 months ago
High github

yutu: Arbitrary File Write via MCP `caption-download` Tool

## Arbitrary File Write via MCP `caption-download` Tool ### Summary The `caption-download` MCP tool in yutu passes the caller-supplied `file` parameter directly to `os.Create()` at `pkg/caption/capt...

Prompt Injection Agentic / MCP prompt injection mcp server ai agent
7.7
CVSS
4 months ago
Low osv

LangSmith SDK: Public prompt pull deserializes untrusted manifests without trust boundary warning

## 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 Lan...

3.1
CVSS
4 months ago
Low osv

LangChain vulnerable to unsafe deserialization of attacker-controlled objects through overly broad `load()` allowlists

LangChain contains older runtime code paths that deserialize run inputs, run outputs, or other application-controlled payloads using overly broad object allowlists. These paths may call `load()` with...

3.1
CVSS
4 months ago
Critical github

Duplicate Advisory: PraisonAI: CodeAgent Executes LLM-Generated Code Without Sandboxing and Leaks All Environment Secrets

### Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-2xv2-w8cq-5gxw. This link is maintained to preserve external references. ### Original Description PraisonAI b...

10.0
CVSS
4 months ago
High github

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 v...

Prompt Injection prompt injection
7.5
CVSS
4 months ago
Unknown rss_bleepingcomputer

'Ghostcommit' hides prompt injection in images to fool AI agents, steal secrets

A PNG hiding a prompt injection could steal your repo's secrets, researchers demonstrate. The technique, dubbed 'Ghostcommit,' slipped past AI code reviewers CodeRabbit and Bugbot, which never open im...

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

mcp-atlassian: Arbitrary file read via missing path validation in confluence_upload_attachment

### Summary `confluence_upload_attachment` passes `file_path` directly to `open(file_path, "rb")` with no path validation. Any authenticated MCP client — or an AI agent manipulated via prompt injectio...

Prompt Injection Agentic / MCP prompt injection ai agent qwen
7.7
CVSS
4 months ago
Medium github

Duplicate Advisory: PraisonAI: Prompt-injection defense blocks only when 3+ detector families fire simultaneously; realistic single-vector injections pass through unblocked

### Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-4r3p-w3mc-5v34. This link is maintained to preserve external references. ### Original Description PraisonAI b...

Prompt Injection prompt injection
5.3
CVSS
4 months ago
Medium nvd

CVE-2026-60086: PraisonAI before 4.6.78 contains a prompt injection defense bypass vulnerability where the injection defense only blocks

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 ma...

Prompt Injection prompt injection
6.9
CVSS
4 months ago
Critical nvd

CVE-2026-55615: Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.5, Neo4jChatAgent

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 validat...

9.2
CVSS
4 months ago
High github

Serena: Unauthenticated Flask dashboard on fixed port enables DNS rebinding → memory poisoning → RCE

### Summary Serena's built-in web dashboard exposes an unauthenticated Flask API on a fixed, predictable port (TCP 24282, hardcoded as `0x5EDA` in `constants.py`). The server has no authentication, n...

Prompt Injection Remote Code Execution prompt injection copilot claude
8.3
CVSS
4 months ago
High nvd

CVE-2026-59807: Composio SDK before 0.2.32-beta.283 contains a path validation bypass vulnerability that allows attackers to read and ex

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...

Prompt Injection prompt injection
8.9
CVSS
4 months ago