39C3: researcher hijacks AI coding assistants with prompt injection
At the 39C3 conference, a security researcher hijacked AI coding assistants with prompt injection. The report is dated 29 December 2025.
Who is affected and how
- security leader
- The permissions of agent-like developer tools must be restricted.
- developer
- Untrusted input reaching AI coding assistants can create a code-execution risk.
- journalist and researcher
- Prompt injection now has a practical demonstration on developer tools.
Sources
- 39C3: Security researcher hijacks AI coding assistants with prompt injectionheise online · Dec 29, 2025
- 39C3: Sicherheitsforscher kapert KI-Coding-Assistenten mit Prompt Injection | heise onlineheise.de · Dec 29, 2025
Machine-generated summary based on the titles and excerpts of the source articles. The facts come from the linked article. News monitoring and analysis, not security advice. Attributions belong to those who made them.
What do you make of this piece?
The split shows after 20 votes.
Why? Your answer is not shown publicly; it helps the editors.