CVE-2026-96893 Improper Neutralization of Input Used for LLM Prompting in GitLab

GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.2.8, 19.3 before 19.3.5, and 19.4 before 19.4.2 that, under certain conditions, could have allowed an authenticated user to inject specially crafted content into AI agent instructions, potentially causing...

CVE-2026-70331

Improper neutralization of input used for llm prompting in Microsoft Edge for iOS allows an unauthorized attacker to perform spoofing over a network...

LLM Prompt Injection Surface Detection

Probes OpenAI-compatible /v1/chat/completions, Ollama, and generic /api/chat endpoints for unauthenticated inference — prompt injection and tool abuse entry points. !/usr/bin/env python3 -- coding: utf-8 -- """Detect exposed LLM chat/completion endpoints prompt injection surface.""" from...

PYSEC-2026-2504 Graphiti vulnerable to Cypher Injection via unsanitized node_labels in search filters

Summary Graphiti versions before 0.28.2 contained a Cypher injection vulnerability in shared search-filter construction for non-Kuzu backends. Attacker-controlled label values supplied through SearchFilters.nodelabels were concatenated directly into Cypher label expressions without validation. In...

CVE-2026-41265

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.0, the specific flaw exists within the run method of the AirtableAgents class. The issue results from the lack of proper sandboxing when evaluating an LLM generated python script. Using prompt...

CVE-2026-32247

Graphiti is a framework for building and querying temporal context graphs for AI agents. Graphiti versions before 0.28.2 contained a Cypher injection vulnerability in shared search-filter construction for non-Kuzu backends. Attacker-controlled label values supplied through SearchFilters.nodelabel...