Supporting Rowhammer research to protect the DRAM ecosystem
…The current state of prompt injections on the web We initiated a broad sweep of the public web to monitor for known indirect prompt injection patterns. This is what we found. By…
Search
All sources
theregister.com
17
blog.google
9
anthropic.com
7
xda-developers.com
7
developer.nvidia.com
6
github.blog
6
huggingface.co
5
blog.cloudflare.com
5
bleepingcomputer.com
4
rockpapershotgun.com
4
pcworld.com
4
appleinsider.com
3
Top stories
People are using prompt injection to trick Meta's AI into handing over Instagram accounts
2d agoHackers hijack thousands of sites for ClickFix and FakeUpdate attacks
3d agoFed up with vibe coders, dev sneaks data-nuking prompt injection into their code
6d agoGhost CMS SQL injection flaw exploited in large-scale ClickFix campaign
1w agoWeb application security Archives
…Encoding and escaping untrusted data to prevent injection attacks Practical tips on how to apply OWASP Top 10 Proactive Control C4. Code scanning and Ruby: turning source code into a queryable database…
Claude Code bypasses safety rule if given too many commands
…This vuln leaves the bot open to prompt injection attacks. Adversa, a security firm based in Tel Aviv, Israel, spotted the issue following the leak of Claude Code's source. Claude Code…
How we contain Claude across products
…External attackers: The agent is attacked through external vectors such as tools, files, or network access. This category includes both prompt injection and conventional attacks on the agent's runtime, orchestration layer…
Discussions and forums
AudioHijack: adversarial audio attacks on generative voice models transfer from open weights to Microsoft and Mistral production systems
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…
Show HN: How to analyze your LLM output – A behavioural health monitor for LLMs
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…
9
5
Trustworthy agents in practice
…Defending against attacks Prompt injections are malicious instructions hidden inside the content that an agent is asked to process. If an agent is searching a user's inbox and one email says…
Reinventing AI Guardrails for a Safer Digital World
…However, the biggest challenge was handling prompt injections. While explicit and overtly malicious expressions are relatively easy to filter out, responding to indirect and sophisticated prompt attacks has only recently become an…
How to kill Blister Heads in Resident Evil Requiem
…If that's the case, you can still go up to a fallen zombie and press the prompted button to use a Hemolytic Injector on them . This isn't ideal though, as…
Moltbook Gives Insights into Agentic AI's Messy Future
…The scans still won’t catch prompt injection attacks because, as mentioned above, these don’t exist in the code of the skill itself but instead in the content the skill might…
macOS ClickFix attacks deliver AppleScript stealers
…to push infostealers via fake CAPTCHA prompts Smooth criminals talking their way into cloud environments, Google says Just like phishing for gullible humans, prompt injecting AIs is here to stay In addition…
VPNs News | Tom's Guide
…VPNs Norton Neo's new in-built VPN claims to boost security without needing user input, and increases protection from prompt injection attacks. Here's what you need to know. VPNs Norton…