Mercor says it was 'one of thousands' hit in LiteLLM attack
Cyber-crime AI recruiting biz Mercor says it was 'one of thousands' hit in LiteLLM supply-chain attack First public downstream victim, but won't be the last AI hiring startup Mercor…
Search
All sources
theregister.com
16
blog.google
9
anthropic.com
7
developer.nvidia.com
6
xda-developers.com
6
huggingface.co
5
blog.cloudflare.com
5
github.blog
4
pcworld.com
4
bleepingcomputer.com
3
spectrum.ieee.org
3
intel.com
3
MCP 'design flaw' puts 200k servers at risk: Researcher
…The third type of vulnerability allows zero-click prompt injection across AI integrated development environments (IDEs) and coding assistants such as Windsurf, Claude Code, Cursor, Gemini-CLI, and GitHub Copilot. However, the…
Security-related product updates - GitHub Blog
…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…
Practical Security Guidance for Sandboxing Agentic Workflows and Managing Execution Risk | NVIDIA Technical Blog
…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…
Top stories
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…
Claude Code bypasses safety rule if given too many commands
…prompt injection – where a malicious CLAUDE.md file instructs the AI to generate a 50+ subcommand pipeline that looks like a legitimate build process." The Adversa team's proof-of-concept attack…
Supporting Rowhammer research to protect the DRAM ecosystem
…It was last updated on March 31, 2026.JanuaryWe terminated 40 Yo… By Trust & Safety May 08, 2026 Security AI threats in the wild: The current state of prompt injections on the…
Discussions and forums
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…
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…
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…