EUVD-2026-60966

CodeWhale: Project config instructions override enables arbitrary file read into AI system prompt via cloned repository...

CVE-2026-31020

In DocsGPT 0.15.0 and below, the application provides a custom prompt feature that allows users to define prompt content used during chatbot interactions. This functionality renders user-supplied prompt data using Jinja templates without input sanitization or sandboxing. An unauthenticated attack...

CVE-2026-19306

IBM Langflow OSS 1.0.0 through 1.11.2 allows an authenticated attacker to read arbitrary files from the server filesystem — including server secret material secretkey, JWT signing keys, the application database, /proc/self/environ, and other tenants' upload directories — by supplying absolute pat...

EUVD-2026-71260

IBM Langflow OSS 1.0.0 through 1.11.2 allows an authenticated attacker to read arbitrary files from the server filesystem — including server secret material secretkey, JWT signing keys, the application database, /proc/self/environ, and other tenants' upload directories — by supplying absolute pat...

CVE-2026-85694

LaVague 0.2.35 contains a remote code execution vulnerability in PythonFromMarkdownExtractor.extractasobject that evaluates untrusted language model output derived from web page content. Attackers can inject malicious Python code through web pages using indirect prompt injection to execute...

CVE-2026-85695

FastChat contains an authentication bypass vulnerability in the /registerworker endpoint that allows unauthenticated attackers to register arbitrary worker addresses and perform server-side request forgery. Attackers can register malicious workers under victim model names to intercept user prompt...

CVE-2026-85675

OWL's DocumentProcessingToolkit contains a server-side request forgery vulnerability in the extractdocumentcontent tool that fetches caller-supplied URLs with no scheme, host, or IP filtering. Attackers can inject malicious URLs through prompt injection to make the server fetch internal resources...

CVE-2026-85695

FastChat (lm-sys/FastChat) has an authentication bypass in the /register_worker endpoint that allows unauthenticated attackers to register arbitrary worker addresses. This enables server-side request forgery (SSRF) and model spoofing : attackers can register malicious workers under victim model n...

CVE-2026-85694 LaVague 0.2.35 Remote Code Execution via eval extraction

LaVague 0.2.35 contains a remote code execution vulnerability in PythonFromMarkdownExtractor.extractasobject that evaluates untrusted language model output derived from web page content. Attackers can inject malicious Python code through web pages using indirect prompt injection to execute...

CVE-2026-85694

LaVague 0.2.35 is vulnerable to remote code execution via its PythonFromMarkdownExtractor.extract_as_object function, which uses eval on untrusted language model output derived from web page content. An attacker can perform indirect prompt injection through a web page to inject malicious Python c...

EUVD-2026-71143

LaVague 0.2.35 contains a remote code execution vulnerability in PythonFromMarkdownExtractor.extractasobject that evaluates untrusted language model output derived from web page content. Attackers can inject malicious Python code through web pages using indirect prompt injection to execute...

CVE-2026-85675

OWL 's DocumentProcessingToolkit contains a server-side request forgery (SSRF) vulnerability in the extract_document_content tool. The tool fetches caller-supplied URLs without scheme, host, or IP filtering , allowing attackers to inject malicious URLs via prompt injection and cause the server to...

CVE-2026-85675 OWL DocumentProcessingToolkit Server-Side Request Forgery via URL Fetching

OWL's DocumentProcessingToolkit contains a server-side request forgery vulnerability in the extractdocumentcontent tool that fetches caller-supplied URLs with no scheme, host, or IP filtering. Attackers can inject malicious URLs through prompt injection to make the server fetch internal resources...

EUVD-2026-71131

OWL's DocumentProcessingToolkit contains a server-side request forgery vulnerability in the extractdocumentcontent tool that fetches caller-supplied URLs with no scheme, host, or IP filtering. Attackers can inject malicious URLs through prompt injection to make the server fetch internal resources...

CVE-2026-85600

Grav Admin getgrav/grav-plugin-admin2 versions , ", or ', allowing an attacker to register a username containing an HTML payload. When an administrator views a UI surface that renders the username through tHtml—such as the two-factor force-disable confirmation prompt or the 'page is locked' edito...

EUVD-2026-71608

In DocsGPT 0.15.0 and below, the application provides a custom prompt feature that allows users to define prompt content used during chatbot interactions. This functionality renders user-supplied prompt data using Jinja templates without input sanitization or sandboxing. An unauthenticated attack...

ASCII smuggling crosses over from AI prompt injection to phishing evasion

In this article 1. What is ASCII smuggling? 2. Writing a practical ASCII-smuggling signature 3. What we observed: ASCII smuggling repurposed for phishing 4. What is known and what is new 5. Is there a detection gap? 6. Mitigation and protection guidance 7. References 8. Learn More Microsoft...

agent-scan v0.6.1

Snyk Agent Scan Discover and scan agent components on your machine for prompt injections and vulnerabilities including agents, MCP servers, skills. Note: We don't publish an npm package for Agent Scan. Install it via uvx or as a standalone binary. Note: CLI output is experimental and subject to...

DRUPAL-CONTRIB-2026-119

This AI Chatbot module enables you to have a Chatbot using assistants to help you with your Drupal website. The module doesn't sufficiently sanitize for cross site scripting XSS when using the structured results using legacy agent setups. This vulnerability is mitigated by the fact that an attack...

Banks: Path traversal in `DirectoryPromptRegistry.set()` allows arbitrary file write outside the registry root

Summary DirectoryPromptRegistry.set interpolates the attacker-controllable Prompt.name into a Path expression with no canonicalization. An application that derives the prompt name from request data lets a caller write attacker-controlled bytes outside the configured registry directory. Details...