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

Unknown rss_securityweek

Critical Vulnerability Exposes GitHub Agentic Workflows to Prompt Injection

Researchers show how attackers can use a crafted public GitHub Issue to trick AI-powered workflows into exposing data from private repositories without authentication. The post Critical Vulnerability...

Prompt Injection Agentic / MCP prompt injection agentic
4 months ago
Low osv

LlamaIndex vulnerable to Creation of Temporary File in Directory with Insecure Permissions

A vulnerability in the `default_jsonalyzer` function of the `JSONalyzeQueryEngine` in the run-llama/llama_index repository allows for SQL injection via prompt injection. This can lead to arbitrary fil...

Prompt Injection llama-index
3.0
CVSS
4 months ago
Medium osv

Langchain SQL Injection vulnerability

A vulnerability in the 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...

4.0
CVSS
4 months ago
Low osv

Langchain Server-Side Request Forgery vulnerability

In Langchain before 0.0.329, prompt injection allows an attacker to force the service to retrieve data from an arbitrary URL, essentially providing SSRF and potentially injecting content into downstre...

3.1
CVSS
4 months ago
Critical github

Langroid: Neo4jChatAgent executes LLM-generated Cypher without validation (prompt-to-Cypher injection; config-conditional RCE), mirroring the SQLChatAgent bug fixed in CVE-2026-25879

Neo4jChatAgent passes LLM-generated Cypher queries straight to the Neo4j driver with no validation, no statement-type allowlist, and no opt-out gate. The query text is influenceable by prompt injectio...

0.0
CVSS
4 months ago
Critical github

Langroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent

### Advisory Details **Title**: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent **Description**: ### Summary Langroid is vulnerable to a critical Sandbox...

Prompt Injection Remote Code Execution prompt injection deepseek openai llm
10.0
CVSS
4 months ago
Medium nvd

CVE-2026-14898: The OpenAI Codex desktop app for macOS rendered remote images from Markdown in model responses. An attacker who could pl

The OpenAI Codex desktop app for macOS rendered remote images from Markdown in model responses. An attacker who could place an indirect prompt injection in content processed by Codex, such as a connec...

Prompt Injection prompt injection indirect prompt openai
6.5
CVSS
4 months ago
Unknown rss_securityweek

Prompt Injection Attacks Trick AI Agents Into Making Crypto Payments

Researchers uncovered two campaigns embedding indirect prompt injections in malicious websites to exploit autonomous AI agents browsing the web. The post Prompt Injection Attacks Trick AI Agents Into...

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

CVE-2026-13341: A vulnerability exists in the Kong Konnect Model Context Protocol (MCP) server prior to version 1.0.0, which could allow

A vulnerability exists in the Kong Konnect Model Context Protocol (MCP) server prior to version 1.0.0, which could allow a remote attacker to perform an indirect prompt injection attack and execute un...

Prompt Injection Agentic / MCP model context protocol prompt injection indirect prompt
7.4
CVSS
4 months ago
Unknown rss_securityweek

Critical Cursor AI Code Editor Flaws Could Lead to OS-Level Remote Code Execution

The DuneSlide vulnerabilities enable zero-click prompt injection attacks that escape Cursor's sandbox and execute arbitrary code on the underlying operating system. The post Critical Cursor AI Code Ed...

4 months ago
Critical github

mcp-memory-service: Missing Authentication on Document API Endpoints Allows Unauthenticated Memory Read/Write/Delete

## Missing Authentication on Document API Endpoints Allows Unauthenticated Memory Read/Write/Delete ### Summary All HTTP routes under `/api/documents/*` in `mcp-memory-service` are served without an...

Prompt Injection Auth Bypass Agentic / MCP prompt injection transformers huggingface ai agent pytorch
9.8
CVSS
4 months ago
Unknown rss_thehackernews

Critical Cursor Flaws Could Let Prompt Injection Escape Sandbox and Run Commands

Two flaws in Cursor, an AI code editor, could let a single, ordinary-looking prompt break out of the editor's safety sandbox and run any command on a developer's computer. There is no click to fall fo...

Prompt Injection prompt injection cursor
4 months ago
Unknown rss_thehackernews

Anthropic Restores Claude Fable 5 After U.S. Lifts Jailbreak-Linked Export Controls

Anthropic is putting Claude Fable 5 back online worldwide. On June 30, the U.S. Commerce Department lifted the export controls it had imposed on Fable and its more tightly controlled sibling Mythos 5...

Prompt Injection claude code anthropic jailbreak claude
4 months ago
Unknown rss_bleepingcomputer

New BioShocking attack manipulates AI browser into data theft

A new prompt injection attack dubbed "BioShocking" could trick AI-powered browsers into treating real-world risky actions as part of a fictional scenario, causing them to ignore any safety guardrails....

Prompt Injection prompt injection
4 months ago
High nvd

CVE-2026-10564: IBM Langflow OSS 1.0.0 through 1.9.6 contains a Server-Side Request Forgery (SSRF). The legacy RSSReaderComponent in rss

IBM Langflow OSS 1.0.0 through 1.9.6 contains a Server-Side Request Forgery (SSRF). The legacy RSSReaderComponent in rss.py and SearXNG component in searxng.py make unvalidated HTTP requests to user-c...

Prompt Injection SSRF Agentic / MCP prompt injection langflow agentic
8.2
CVSS
4 months ago
High nvd

CVE-2026-55607: Claude Code is an agentic coding tool. From 2.1.38 until 2.1.163, Claude Code's worktree handling allowed creation of w

Claude Code is an agentic coding tool. From 2.1.38 until 2.1.163, Claude Code's worktree handling allowed creation of worktrees named ".git" and navigation to worktrees outside the sandbox context, e...

Prompt Injection Agentic / MCP prompt injection claude code agentic claude
7.7
CVSS
4 months ago
Unknown rss_securityweek

Researchers Demo New Claude Code Attack Using Harmless-Looking Repositories to Hijack Developer Machines

Indirect prompts hidden in a repository can lead to Claude Code spawning a reverse shell on the developer’s machine. The post Researchers Demo New Claude Code Attack Using Harmless-Looking Repositorie...

Prompt Injection indirect prompt claude code claude
4 months ago
Low osv

Langchain SQL Injection vulnerability

In Langchain before 0.0.247, prompt injection allows execution of arbitrary code against the SQL service provided by the chain.

3.1
CVSS
4 months ago
Low osv

LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs

## Summary A serialization injection vulnerability exists in LangChain's `dumps()` and `dumpd()` functions. The functions do not escape dictionaries with `'lc'` keys when serializing free-form dictio...

3.1
CVSS
4 months ago
Unknown rss_bleepingcomputer

New macOS malware embeds fake errors to confuse AI analysis tools

A newly discovered macOS malware dubbed "Gaslight" is designed to confuse AI-assisted malware analysis tools by hiding prompt injection strings and fake debugging data within the executable. [...]

Prompt Injection prompt injection
4 months ago
Unknown rss_thehackernews

New Gaslight macOS Malware Uses Prompt Injection to Disrupt AI-Assisted Analysis

A previously undocumented Rust-based macOS implant and information stealer has been found to embed a prompt injection payload designed to trick a malware analyst's artificial intelligence (AI) tools a...

Prompt Injection prompt injection
4 months ago
High nvd

CVE-2025-66389: GitHub Copilot 1.372.0 allows filesystem access outside of a workspace folder (without user approval) via a file-handler

GitHub Copilot 1.372.0 allows filesystem access outside of a workspace folder (without user approval) via a file-handler URI parameter to fetch_webpage. Therefore, exfiltration could occur if there is...

Prompt Injection prompt injection indirect prompt github copilot copilot
7.5
CVSS
4 months ago
Critical github

Duplicate Advisory: Flowise OverrideConfig security vulnerability

### Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-5cph-wvm9-45gj. This link is maintained to preserve external references. ### Original Description Flowise bef...

9.8
CVSS
4 months ago
Critical nvd

CVE-2024-58351: Flowise before 2.1.4 allows configuration to be injected into the Chainflow during execution via the overrideConfig opti

Flowise before 2.1.4 allows configuration to be injected into the Chainflow during execution via the overrideConfig option, supported in both the frontend web integration and the backend Prediction AP...

9.3
CVSS
4 months ago
High github

SearXNG MCP Server: DNS-resolved Private Hostname SSRF in `web_url_read`

## DNS-resolved Private Hostname SSRF in `web_url_read` ### Summary The `web_url_read` MCP tool in `mcp-searxng` is vulnerable to Server-Side Request Forgery (SSRF) via DNS rebinding bypass. The `as...

Prompt Injection SSRF Agentic / MCP prompt injection mcp server ai agent
7.1
CVSS
4 months ago