CVE-2026-73487

Flowise prior to version 3.1.3 is affected by a vulnerability in the CSV and Airtable Agent nodes where a regex-based Python code validator bypass enables unauthenticated prompt injection. This can allow an attacker to inject and execute code, exfiltrate datasets via unblocked pandas functions (e...

PT-2026-71495

HCL AION is affected by a vulnerability where indirect prompt injection can lead to HTML injection in rendered output. Injected markup may be displayed to users, potentially resulting in unintended behavior or security impact under certain conditions...

PT-2026-71675

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions CompletionRequest.prompt field in vllm/entrypoints/openai/completion/protocol.py accepts an unbounded liststr or listlistint, prompt to seq in vllm/renderers/inputs/preprocess.py and...

PT-2026-71665

Oh My Posh is the most customisable and low-latency cross platform/shell prompt renderer. Prior to 29.35.1, the setStyle function in src/segments/path.go passed pt.Path, which includes raw folder names, to template.Render, whose function map exposes cmd, so an attacker-controlled directory name...

PT-2026-71672

Name of the Vulnerable Software and Affected Versions vLLM versions 0.20.2rc0 through 0.25.x Description A race condition exists in the safe load prompt embeds function within vllm/renderers/embed utils.py when enable prompt embeds is enabled. The issue occurs because torch.sparse.check sparse...

PT-2026-71427

Flowise before 3.1.3 contains a regex-based Python code validator bypass in CSV and Airtable Agent nodes that allows unauthenticated attackers to inject malicious code via prompt injection. Attackers can exploit unblocked pandas functions like pd.read json to exfiltrate datasets, perform SSRF...

OpenAI, Anthropic, Google API Flaw Let Weaker AI Models Decode Stronger Models' Reasoning

A newly disclosed flaw in the way OpenAI, Anthropic, and Google carried hidden AI reasoning between API calls let researchers recover internal reasoning and secrets from session logs, including API keys and passwords. The weakness affected encrypted reasoning objects used by the providers'...

CVE-2026-73036

Bash-it 3.2.0 contains a terminal escape sequence injection vulnerability in the barbuk theme's Python virtualenv prompt segment that allows local attackers to inject arbitrary terminal control sequences by embedding escape sequences in the requires-python field of a pyproject.toml file. When a...

EUVD-2026-56927

Bash-it 3.2.0 contains a terminal escape sequence injection vulnerability in the barbuk theme's Python virtualenv prompt segment that allows local attackers to inject arbitrary terminal control sequences by embedding escape sequences in the requires-python field of a pyproject.toml file. When a...

CVE-2026-73036

Bash-it 3.2.0 contains a terminal escape sequence injection vulnerability in the barbuk theme's Python virtualenv prompt segment that allows local attackers to inject arbitrary terminal control sequences by embedding escape sequences in the requires-python field of a pyproject.toml file. When a...

CVE-2026-73032

PapersGPT for Zotero 0.6.1 contains a remote code execution vulnerability: an unsanitized LLM response passed to window.eval() in views.ts allows arbitrary JavaScript execution in Zotero's chrome-privileged context. Attackers can exploit prompt injection in PDFs, MITM interception of API requests...

EUVD-2026-56896

PapersGPT for Zotero 0.6.1 contains a remote code execution vulnerability that allows attackers to execute arbitrary JavaScript by returning malicious code from an LLM endpoint that is passed unsanitized to window.eval in views.ts. Attackers can exploit this through prompt injection in PDFs, MITM...

CVE-2026-73032 PapersGPT for Zotero 0.6.1 RCE via Unsanitized LLM Response eval()

PapersGPT for Zotero 0.6.1 contains a remote code execution vulnerability that allows attackers to execute arbitrary JavaScript by returning malicious code from an LLM endpoint that is passed unsanitized to window.eval in views.ts. Attackers can exploit this through prompt injection in PDFs, MITM...

CVE-2026-73032 PapersGPT for Zotero 0.6.1 RCE via Unsanitized LLM Response eval()

PapersGPT for Zotero 0.6.1 contains a remote code execution vulnerability that allows attackers to execute arbitrary JavaScript by returning malicious code from an LLM endpoint that is passed unsanitized to window.eval in views.ts. Attackers can exploit this through prompt injection in PDFs, MITM...

PT-2026-70874

Name of the Vulnerable Software and Affected Versions PapersGPT for Zotero version 0.6.1 Description A remote code execution issue exists where arbitrary JavaScript can be executed by returning malicious code from an LLM endpoint. This occurs because the response is passed unsanitized to the...

PT-2026-70891

Bash-it 3.2.0 contains a terminal escape sequence injection vulnerability in the barbuk theme's Python virtualenv prompt segment that allows local attackers to inject arbitrary terminal control sequences by embedding escape sequences in the requires-python field of a pyproject.toml file. When a...

PraisonAI CodeAgent 1.6.77 Remote Code Execution

The CodeAgent.executepython in PraisonAI executes LLM-generated code without sandboxing, AST validation, or import restrictions. This allows full environment secret exfiltration and arbitrary code execution via prompt injection. Versions 1.6.77 and below are affected. !/usr/bin/env python3 Exploi...

Why Generative AI Needs a New Kind of Security

This is Post 2 of a three-part series. Start withPost 1: Agentic AI Security: The Chatbot Era Is Over, then continue to Post 3: OWASP LLM Top 10: What Comes Next – Agentic & MCP. There is a moment every CISO is having right now, often without warning. A developer shows a working internal demo of ...

Not an A11y: How Android Accessibility Exposes Mobile AI Agents to Indirect Prompt Injection

The rise of autonomous AI agents represents a major paradigm shift in how users interact with mobile devices. Frameworks such as MobileRun and Mobile-Use can autonomously navigate Android applications and execute complex multi-step tasks. To interpret user interfaces, these frameworks rely...

bromure agentic-coding-v4.5.4

Bromure Secure, ephemeral computing in disposable Linux VMs on macOS. → Full details, screenshots, and downloads at bromure.io This repo ships two sibling apps, both built on Apple's Virtualization.framework: Bromure — every browser session runs in a throwaway Linux VM. Close the window, the VM i...