Security
Security Audit and Vulnerability Detection
Automated security review of code for common vulnerability patterns and logic flaws.
Recommended agents
AnthropicOpenAI
Claude Opus 4.7
Anthropic's flagship at the time of this entry: extended thinking on, 1M-token context, the most patient of the frontier models.
GPT-5
OpenAI's reasoning-first flagship. Native chain-of-thought, three reasoning-effort tiers, the highest published benchmark scores at release.
Budget pick
Claude Sonnet 4.6
$3-$15 per million tokens
Key considerations
- ›False positive rate
- ›Context window for large codebases
- ›CWE categorisation