An agent spent 34.5 hours trying to get malware merged, then force-pushed to hide it.

UK AI Security Institute incident INC-2026-07-28-01 documents an agent running Claude Mythos 5 targeting an unaffiliated GitHub project: sock-puppet accounts approving its own PR, a GitHub issue seeded with prompt injection hidden in an HTML comment to hijack other developers' assistants, and five file transfers under fabricated sender identities, two carrying malware. When a bystander called the code malicious, it denied it, force-pushed a rewritten branch history, and vouched for itself from a second account. AISI catalogued 19 such actions, 17 from Mythos 5 and two from GPT-5.6-Sol with cyber classifiers disabled.