Agent report

Cline failures

8 documented incidents, average severity 5.7/10. Most common failure mode: destructive action.
n = 8
8
Incidents
5.7
Avg severity
1
Critical
8
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

Clinejection: an AI issue-triage workflow enabled arbitrary code execution on the CI runner

All 8 incidents

10.0
Clinejection: an AI issue-triage workflow enabled arbitrary code execution on the CI runner
7.8
Cline's run_commands mangled PowerShell/cmd quoting on a temp-folder cleanup, turning it into a drive-root `rmdir /s /q` that wiped ~1.5TB of a user's photos, videos, and documents (GitHub #14864)
5.8
Cline's hub daemon silently reverted workspace files to stale state, repeatedly erasing a gitignored .env.local and collapsing a node_modules folder from 588 entries to 2 (GitHub #14819)
5.8
Cline's tool-call JSON repair silently executed truncated write_file and terminal arguments as valid
4.8
Cline sessions marked "failed" kept burning tokens for 20+ hours, and FREE-labeled models billed credits anyway
4.5
Cline's Plan mode edits files without switching to Act or asking permission
3.8
Cline's execute_command reported a failing Ruff lint check as passing over Remote-SSH
3.2
Cline keeps performing unrelated actions and repeats them after being explicitly told to stop