CLAIM-2026-08-01-06

IssueTrojanBench (arXiv 2607.20759, submitted 22 July 2026) evaluates 696 adversarial artifacts across six agent-model configurations — 4,176 runs — against Cursor, Claude Code and Codex Desktop. 66.5% of malicious issues penetrate all guardrails. Per agent: Codex Desktop 79.2%, Cursor 66.5%, Claude Code 41.1%. Cursor's per-agent figure coincidentally equals the benchmark-wide average; the two are computed over different populations.

Why it matters

The numbers are usable in a design review as they stand, and the coincidence is worth naming out loud: a per-item figure matching the headline normally signals a conflation error, and here it does not.

Sources

arxiv2026issuetroj

CLAIM-2026-08-01-06

IssueTrojanBench (arXiv 2607.20759, submitted 22 July 2026) evaluates 696 adversarial artifacts across six agent-model configurations — 4,176 runs — against Cursor, Claude Code and Codex Desktop. 66.5% of malicious issues penetrate all guardrails. Per agent: Codex Desktop 79.2%, Cursor 66.5%, Claude Code 41.1%. Cursor's per-agent figure coincidentally equals the benchmark-wide average; the two are computed over different populations.

Why it matters

Sources

arxiv2026issuetroj