Security

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.

7 capabilities6 low-risk
Curated · 52
MCP Interface Inspector
Skill · Security, Coding +1
68/100
Rec

Parse MCP server metadata, tools, prompts, and resources into a normalized interface report.

Risk reviewedlow riskCodex
MCP Static Audit Workflow
Workflow Template · Security, Automation
67/100
Rec

Normalize an MCP server repo and flag risky permissions, scripts, and auth requirements.

Risk reviewedlow riskCodex
PR Risk Classifier
Skill · Coding, Security
57/100
Indicative

Classify pull requests by blast radius, missing tests, security exposure, and migration risk.

Info checkedlow riskCodex
Agent Trace Reviewer
Skill · Automation, Security
57/100
Indicative

Review agent traces for tool choice, wasted steps, unsafe actions, and recovery quality.

Info checkedlow riskCodex
Policy Compliance Agent
Agent Template · Automation, Security
54/100
Indicative

Check outputs or support actions against a policy document and escalate uncertain cases.

Info checkedmedium riskClaude

Other scenarios