Threat
Prompt Injection in VirusTotal's Code Insights API
Publication date not yet evaluated · Added exploiting.systems
Page published
Coverage timeline
Single-source research — one report is available.
Why it matters
VirusTotal's Code Insights API prompt-injection weakness lets malware authors pollute automated malware-analysis pipelines that rely on the endpoint, evading AI detection or seeding false results.
A researcher discovered prompt-injection flaws in VirusTotal's AI-powered Code Insights API (backed by gemini-2.5-flash), showing that embedded injection strings and false pretext in large block comments can suppress or alter analysis, force undocumented error schemas that leak the backend model, and induce false negatives or false positives. The bugs were accepted by Google's AI VRP on March 25, 2026 and are being patched.