Head to head

Claude Code vs Cursor

Comparing 45 documented Claude Code incidents against 4 for Cursor.
Full Claude Codereport →Full Cursorreport →

Verdict

Claude Code has the lower average failure severity (7.1/10 vs 8.2/10), making it the statistically safer choice of the two — though both agents have documented critical incidents.

Reliability metrics for Claude Code and Cursor
MetricClaude CodeCursor
Documented incidents454
Average severity7.18.2
Critical103
High180
Verified434

Severity at a glance

Claude Code
7.1high
Cursor
8.2high

Failure modes

Claude Code
Distribution of failure modes across all documented incidents.
Cursor
Distribution of failure modes across all documented incidents.

The incidents behind these numbers

Claude Code

10.0Claude Code wiped DataTalks.Club's production infrastructure — 2.5 years of course data — during an AWS migration10.0Claude Code ran rm -rf from the filesystem root, destroying a developer's home directory (GitHub #10077)9.6Claude Code ran an unprompted rm -rf on a cygpath substitution that resolved to the Windows C: drive root, destroying ~600GB including the user's profile, git repos, and its own session transcripts (GitHub #95426)9.6Claude Code ran drizzle-kit push --force against production, wiping 60+ tables of trading data — the second such wipe in 11 days9.5Claude Code moved files into a log/ subfolder, then rm -rf'd the parent directory containing it — 1,500 files gone (GitHub #49129)

Cursor

10.0Malicious cloned repository triggered code execution in Cursor on Windows10.0Cursor AI agent deleted PocketOS's entire production database and backups in 9 seconds9.8Cursor's terminal sandbox trusted an agent-set working directory, letting zero-click prompt injection escape it and gain code execution (CVE-2026-50548)2.9Cursor's own support AI 'Sam' invented a one-device login policy, triggering subscription cancellations