A security researcher tricks Claude's web_fetch tool into leaking user data via a honeypot attack, bypassing Anthropic's protections.
A security researcher tricked Claude's web_fetch tool into leaking private user data by exploiting a loophole in URL navigation rules.
Guide to preventing prompt injection attacks in AI systems, covering real-world examples and defense strategies.
Explains ChatGPT Lockdown Mode, a security feature preventing prompt injection attacks by disabling outbound data channels.
Explores security and safety checks for AI agents beyond capability, focusing on contextual integrity, policy, and authority.
OpenAI introduces Lockdown Mode to prevent data exfiltration from prompt injection attacks in ChatGPT.
OpenAI introduces Lockdown Mode to prevent data exfiltration from prompt injection attacks in ChatGPT.
Analysis of Microsoft's AI Prompt Defense Stack, including Prompt Shields, Spotlighting, and Defender for Cloud, to protect against prompt injection attacks.
Hackers exploited Meta's AI chatbot to hijack high-profile Instagram accounts by simply asking it to change account recovery details.
A research paper warns that web agents are vulnerable to confusion attacks from deceptive web pages, not just prompt injection.
Explores whether prompt injection in AI systems is an unsolvable structural problem or just an unfixed vulnerability.
Explains 'Disregard that!' attacks, a prompt injection vulnerability in LLMs where users manipulate the context window to hijack AI behavior.
Report on a prompt injection attack in Snowflake's Cortex AI agent that allowed malware execution, now fixed.
Report on a prompt injection attack that allowed Snowflake's Cortex AI agent to escape its sandbox and execute malware.
A detailed analysis of a prompt injection attack against Cline's GitHub repo, exploiting AI issue triage to poison caches and compromise production releases.
A detailed analysis of a prompt injection attack against Cline's GitHub repo, leading to cache poisoning and a compromised NPM release.
A security vulnerability in Claude Cowork allowed file exfiltration via the Anthropic API, bypassing default HTTP restrictions.
Security researchers found a vulnerability in Claude Cowork allowing data exfiltration via the Anthropic API, bypassing default HTTP restrictions.
A prompt injection attack on Superhuman AI exposed sensitive emails, highlighting a critical security vulnerability in AI email assistants.
A prompt injection attack on Superhuman AI exposed sensitive emails, highlighting a security vulnerability in third-party integrations.
