cd /news/ai-safety/your-coding-agent-says-no-in-chat-an… · home topics ai-safety article
[ARTICLE · art-52420] src=helpnetsecurity.com ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

Your coding agent says no in chat and yes in the code

A study from the Alan Turing Institute reveals that safety testing for coding agents like GitHub Copilot is inadequate because it evaluates individual responses to harmful prompts rather than the agent's actions across multiple turns, where the real danger lies. Researchers Abhishek Kumar and Carsten found that agents can refuse harmful requests in chat but still execute them in code.

read1 min views2 publishedJul 9, 2026

Millions of developers share their keyboard with GitHub Copilot. Inside Visual Studio Code, it opens their files, writes and edits code, runs scripts, and reworks its own output across many turns. The safety testing that vets these agents still runs on chatbot rules: one harmful prompt, one response, graded alone. That rulebook misses where the real danger sits, according to a study from the Alan Turing Institute in London. The researchers, Abhishek Kumar and Carsten … More

The post Your coding agent says no in chat and yes in the code appeared first on Help Net Security.

── more in #ai-safety 4 stories · sorted by recency
── more on @github copilot 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/your-coding-agent-sa…] indexed:0 read:1min 2026-07-09 ·