…expand the attack surface beyond traditional prompt injection. It also offers pragmatic strategies for mitigating indirect AGENTS.md injection attacks in agentic environments. Understanding and recognizing these nuanced attack paths and implementing…
…Direct prompt injection: The attacker is the user, and provides inputs via normal user interactions. Impact is typically scoped to the attacker’s session but is useful for probing behaviors. Indirect prompt…
…prompts were all writable, meaning an attacker could poison everything Lilli spits out to all of the tens of thousands of consultants using the chatbot. CodeWall's agent found the SQL injection…
…0-click prompt injection "What we're seeing now is that because agents gain access to data that they can browse at will, this becomes an attack factor that leads to zero…
Interesting new research you may have heard of on attacking large audio language models. The attack is called AudioHijack and the part worth paying attention to is that adversarial clips built against open models transfe…
Hey HN! We're Dr. Kashyap Thimmaraju and Giuseppe Canale from Silicon Psyche. We've built Posture Sequence Analysis (PSA), a behavioural health monitor for LLMs and AI Agents.Why we built PSAWe built PSA because we wante…
…Xu said organizations that encourage users to experiment with AI may inadvertently see them conduct prompt injection attacks. Policy and education should control this risk, he said, as will the content safety…
…A prompt injection attempt is suspicious. A prompt injection attempt from an IP that’s been probing your login page, using a browser fingerprint associated with previous attacks, and rotating through a…
…of companies impacted by a supply chain attack involving LiteLLM," Mercor said on social media in a Tuesday post. "Our security team moved promptly to contain and remediate the incident," the statement…
…All roads lead to RCE The first type of vulnerability, unauthenticated and authenticated command injection, allows an attacker to enter user-controlled commands that will run directly on the server without authentication…
…Based on the NVIDIA AI Red Team ’s experience, the following mandatory controls mitigate the most serious attacks that can be achieved with indirect prompt injection: Network egress controls: Blocking network access…
…registry attacks, GitHub is strengthening npm’s security with stricter authentication, granular tokens, and enhanced trusted publishing to restore trust in the open source ecosystem. Safeguarding VS Code against prompt injections When…