Attack  ·  Glossary

Indirect Prompt Injection via Repository Artifacts

An attack where malicious files in a code repository (such as task definitions, configuration files, or prompt templates) silently poison an AI agent's system prompt or behavior when the developer opens the repository. The agent executes attacker-specified instructions without the developer's knowledge.
In AI-enhanced development workflows, repositories are trusted contexts; attackers can weaponize the repository itself to reprogram the AI agent's goals, hide exfiltration, or enable lateral movement, all without modifying code.
References
Eclipse Foundation - Security Advisories
Track this in the live feed See how this plays out in real AI security and governance developments.
Open the feed →