Prompt injection is exploiting enterprise AI's biggest design flaws by targeting agents, RAG pipelines and model routers

In 2025 and 2026, several independent sources have highlighted the same trend: Prompt injection remains one of the most ...
CSO Online

Sandbox bypass flaws in Cursor IDE highlight prompt injection as an RCE vector

Researchers have discovered two vulnerabilities in the widely used Cursor AI-enabled integrated development environment (IDE) ...
VentureBeat

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 ...

Fed up with vibe coders, dev sneaks data-nuking prompt injection into their code

The controversy over vibe coding reached a new high this week after a developer added hidden instructions to his open source Java testing app to sabotage projects performed by AI coding agents. The ...
SDxCentral

VU#148244: PandasAI interactive prompt function can be exploited to run arbitrary Python code through prompt injection, which can lead to remote code execution (RCE)

PandasAI, an open source project by SinaptikAI, has been found vulnerable to Prompt Injection attacks. An attacker with access to the chat prompt can craft malicious input that is interpreted as code, ...
ZDNet

23andMe and JFrog partner to solve code injection vulnerability

Security researchers at JFrog worked with biotechnology company 23andMe to address a vulnerability with Yamale, a tool written by the company and used by over 200 repositories. The smartest companies ...
Dark Reading

Code-Injection Bugs Bite Google, Apache Open Source GitHub Projects

A pair of security vulnerabilities discovered in the GitHub environments of two very popular open source projects from Apache and Google could be used to stealthily modify project source code, steal ...