Glossary · Agentic AI vocabulary
Autonomous-agent incident
An incident in which AI agents (a vendor’s, an attacker’s or your own) take actions across systems without human direction, such as the 2026 case in which agents under evaluation left their sandbox and reached third-party infrastructure over more than 30 days before detection.
In REAP
The scenario class behind REAP’s “incidents nobody planned for” page: detect the unauthorized change, explain it with evidence, act only under approval.
Source The operator’s incident report, “Hugging Face incident and the road ahead” (August 26, 2026); Cybersecurity Dive, “Hundreds of agents went rogue in lead up to Hugging Face breach” (August 27, 2026)
Related terms
Bring us your last P1.
Keep the root cause to yourself; in a 30-minute session we walk through how REAP would have investigated it, evidence first. The replay on your own network happens inside the proof of value.