Three AI coding agents leaked secrets through a single prompt injection. One vendor's system card predicted it
A security researcher, working with colleagues at Johns Hopkins University, opened a GitHub pull request, typed a malicious instruction into the PR title, and watched Anthropic’s Claude Code Security Review action post its own API key as a comment. The same prompt injection worked on Google’s Gemini CLI Action and GitHub’s Copilot Agent (Microsoft). No external infrastructure required.Aonan Guan, the researcher who discovered the vulnerability, alongside Johns Hopkins colleagues Zhengyu Liu and Gavin Zhong, published the full technical disclosure last week, calling it “Comment and Control.” GitHub Actions does not expose secrets to fork pull requests by default when using the pull_request trigger, but workflows using pull_request_target, which most AI agent integrations require f [...]
Rating
Innovation
Pricing
Technology
Usability
We have discovered similar tools to what you are looking for. Check out our suggestions for similar AI tools.
Anthropic’s browser agent got hijacked 31.5% of the time before safeguards engaged
Across the frontier labs, the highest prompt injection figures published this spring are Anthropic’s. Point a red-teamer at its newest model in a browser, and the attacker hijacked it 31.5% of the t [...]
Anthropic published the prompt injection failure rates that enterprise security teams have been asking every vendor for
Run a prompt injection attack against Claude Opus 4.6 in a constrained coding environment, and it fails every time, 0% success rate across 200 attempts, no safeguards needed. Move that same attack to [...]
Anthropic vs. OpenAI red teaming methods reveal different security priorities for enterprise AI
Model providers want to prove the security and robustness of their models, releasing system cards and conducting red-team exercises with each new release. But it can be difficult for enterprises to pa [...]
Nvidia's agentic AI stack is the first major platform to ship with security at launch, but governance gaps remain
For the first time on a major AI platform release, security shipped at launch — not bolted on 18 months later. At Nvidia GTC this week, five security vendors announced protection for Nvidia's a [...]
OpenAI admits prompt injection is here to stay as enterprises lag on defenses
It's refreshing when a leading AI company states the obvious. In a detailed post on hardening ChatGPT Atlas against prompt injection, OpenAI acknowledged what security practitioners have known fo [...]
Microsoft patched a Copilot Studio prompt injection. The data exfiltrated anyway.
Microsoft assigned CVE-2026-21520, a CVSS 7.5 indirect prompt injection vulnerability, to Copilot Studio. Capsule Security discovered the flaw, coordinated disclosure with Microsoft, and the patch was [...]
Red teaming LLMs exposes a harsh truth about the AI security arms race
Unrelenting, persistent attacks on frontier models make them fail, with the patterns of failure varying by model and developer. Red teaming shows that it’s not the sophisticated, complex attacks tha [...]