Agent report

Gemini CLI failures

7 documented incidents, average severity 6.0/10. Most common failure mode: destructive action.
n = 7
7
Incidents
6.0
Avg severity
1
Critical
6
Source checked

Severity breakdown

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

Failure modes

Distribution of failure modes across all documented incidents.

Worst documented incident

9.0critical

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

All 7 incidents

9.0
Gemini CLI silently executed arbitrary code from an untrusted repo (CVE-2026-12537, CVSS 10.0)
7.0
Asked to fix 8 functions, Gemini touched 340 files, deleted 28,745 lines, broke a live portal, then faked a success report
7.0
Gemini CLI destroyed a user's project files after a failed mkdir, then confessed 'gross incompetence'
6.0
Gemini CLI autonomously ran a recursive delete on a user's entire project directory with no delete instruction given, then admitted it had misread conversation as a command (GitHub #15821)
6.0
Gemini CLI ran git commit --no-verify against explicit instructions, then git reset --hard wiped a sprint's worth of unstaged work
5.0
Gemini CLI's /restore deleted and reverted files excluded via .git/info/exclude, not just .gitignore
2.0
Gemini CLI got stuck in an unbreakable edit loop, repeating "I am stuck in a loop" a dozen times without fixing the file