Claude Code, Gemini CLI and GitHub Copilot agents vulnerable to prompt injection via comments
According to an April 16 report, the Claude Code, Gemini CLI and GitHub Copilot agents are vulnerable to prompt injection through comments.
Who is affected and how
- security leader
- The permissions and access of developer agents should be narrowed.
- developer
- Code comments and external content should be treated as untrusted input when an agent works with them.
Sources
- Claude Code, Gemini CLI, GitHub Copilot Agents Vulnerable to Prompt Injection via Comments - SecurityWeeksecurityweek.com · Apr 16, 2026
- AI agents on GitHub leak API keys via prompt injection - Techzine Globaltechzine.eu · Apr 16, 2026
- ‘Comment and Control’ attack can hack Claude Code, Gemini CLI and GitHub Copilot at oncedigitaltoday.co.kr · Apr 16, 2026
- นักวิจัยใช้ Prompt Injection เจาะ AI Agents ขโมย API Keys จาก Claude, Gemini และ Copilot ได้สำเร็จ | Techsaucetechsauce.co · Apr 16, 2026
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.