Intuit: Contributor to HalluSquatting Research
Intuit, represented by researcher Ron Bitton, collaborated with Tel Aviv University and Technion on the HalluSquatting attack research.
Tag: AI Security
Tel Aviv University: Leading HalluSquatting Research
Tel Aviv University researchers, including Aya Spira and Ben Nassi, discovered the HalluSquatting attack exploiting AI coding assistants.
Technion: Collaborator in HalluSquatting Research
Technion researcher Stav Cohen contributed to the HalluSquatting attack study alongside Tel Aviv University and Intuit.
GitHub Copilot Refuses Harmful Requests in Chat, Then Writes Them in Code
Researchers Abhishek Kumar and Carsten Maple have discovered a novel workflow-level jailbreak method that bypasses safety guardrails in GitHub Copilot. The study,…
CISA Adds 4 Actively Exploited Adobe, Joomla, and Langflow Flaws to KEV Catalog
The U.S. Cybersecurity and Infrastructure Security Agency (CISA) has added four security flaws to its Known Exploited Vulnerabilities (KEV) catalog, citing evidence…
Rogue Agent Flaw in Google Dialogflow CX Could Let Attackers Hijack AI Chatbots
A critical vulnerability in Google's Dialogflow CX, dubbed 'Rogue Agent' by security firm Varonis, could have allowed an attacker with edit permissions…
Writer AI Flaw Could Let Agent Previews Leak Session Tokens Across Tenants
Cybersecurity researchers at Sand Security have disclosed a now-patched critical session isolation vulnerability in Writer, an enterprise generative AI platform. The flaw,…
GitLost Attack: Public GitHub Issue Tricks AI Agents Into Leaking Private Repo Data
Researchers at Noma Security have demonstrated a novel prompt injection attack, dubbed GitLost, that exploits GitHub Agentic Workflows to leak private repository…
Noma Security Discovers Critical Ruflo Vulnerability RufRoot
Noma Security's research team, Noma Labs, identified and disclosed the RufRoot vulnerability (CVE-2026-59726) in Ruflo. The flaw enables unauthenticated attackers to execute…
GitHub Agentic Workflows Feature Vulnerable to GitLost Prompt Injection
GitHub Agentic Workflows, a feature in public preview, allows AI agents to automate tasks but is vulnerable to indirect prompt injection attacks…