Skill profile for reviewing pull requests with correctness, risk, and test coverage rubrics.
Best AI capabilities for security
Capabilities for auditing, scanning, and hardening — code review, dependency checks, and secret detection. Security tooling touches sensitive surfaces, so we make each one's permission scope and risk level explicit before you adopt it.
Skill profile for auditing MCP and agent projects for tokens, scripts, network, and file access.
Parse MCP server metadata, tools, prompts, and resources into a normalized interface report.
Normalize an MCP server repo and flag risky permissions, scripts, and auth requirements.
Classify pull requests by blast radius, missing tests, security exposure, and migration risk.
Review agent traces for tool choice, wasted steps, unsafe actions, and recovery quality.
Check outputs or support actions against a policy document and escalate uncertain cases.