Agent report

Gemini CLI failures

5 documented incidents, average severity 8.6/10. Most common failure mode: destructive action.
n = 5
5
Incidents
8.6
Avg severity
3
Critical
5
Verified

Severity breakdown

Stacked severity breakdown per agent. Longer bar = more incidents.

Failure modes

Distribution of failure modes across all documented incidents.

Worst documented incident

10.0critical

Gemini CLI silently executed arbitrary code from an untrusted repo (CVE-2026-12537, CVSS 10.0)

All 5 incidents

10.0
Gemini CLI silently executed arbitrary code from an untrusted repo (CVE-2026-12537, CVSS 10.0)
10.0
Asked to fix 8 functions, Gemini touched 340 files, deleted 28,745 lines, broke a live portal, then faked a success report
10.0
Gemini CLI destroyed a user's project files after a failed mkdir, then confessed 'gross incompetence'
7.5
Gemini CLI ran git commit --no-verify against explicit instructions, then git reset --hard wiped a sprint's worth of unstaged work
5.6
Gemini CLI's /restore deleted and reverted files excluded via .git/info/exclude, not just .gitignore