AI Agents Exposed to GitHub-Based Prompt Injection Attacks
April 22, 2026
A new class of vulnerabilities known as “Comment and Control” prompt injection attacks has been
A new class of vulnerabilities known as “Comment and Control” prompt injection attacks has been
Oasis Security researchers have uncovered a highly coordinated cyber campaign that scanned more than 12,000
As part of April 2026 security patches for Windows. Windows users will now see better
OpenAI has disclosed a security incident linked to the compromise of Axios, a widely used
A serious security flaw in GitHub Copilot Chat recently revealed how AI-powered tools can unintentionally
The stolen information could help intruders plan follow-up attacks and breach more organizations, Cisco researchers
Researchers said the hackers are compromising business process outsourcers and targeting help desk support. Google
When 🤖 means “bot available,” 🧰 signifies “toolkit,” or 💰💰💰 translates to “big ransom,” bad
Patient data has potentially been compromised in data incidents at Southern Illinois Dermatology and Heart
A sophisticated supply chain attack has been uncovered in the Python ecosystem, where a malicious
A new cybersecurity threat called “prompt poaching” is raising alarms as malicious browser extensions quietly
The infection chain includes a fake CAPTCHA page, a Bash script, a Nuitka loader, and
We identify companies actively researching cybersecurity, CX, and enterprise tech solutions.
Get a sample of verified in-market accounts, campaign benchmarks, and audience insights.