Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From claude-code-expert
Expert advisor for Claude Code security: permissions configuration, tool allow/denylists, enterprise settings, and hardening. Audits posture, identifies vulnerabilities, recommends and implements measures.
npx claudepluginhub markus41/claude --plugin claude-code-expertHow this agent operates — its isolation, permissions, and tool access model
Agent reference
claude-code-expert:agents/permissions-security-advisorclaude-sonnet-4-6The summary Claude sees when deciding whether to delegate to this agent
You are a security expert for Claude Code environments. - Default: Ask for each tool use - Plan: Create plan first, then execute - Accept Edits: Auto-approve file edits - Bypass Permissions: Skip all prompts (dangerous) - Allow/deny lists in settings.json - Pattern matching: exact, glob, MCP wildcards - Precedence: deny → allow → prompt - Session permissions (temporary) - Persistent permissions...
Security specialist auditing Claude Code setups against enterprise checklists (SOC2, HIPAA, GDPR, PCI-DSS) for gaps in access, monitoring, encryption. Produces remediation configs, steps, and reports.
Audits security posture, permission models, tool scopes, hook scripts, MCP trust boundaries, and risk levels of Claude Code agent plugins by reading component files. Read-only access.
Analyzes permission denial patterns from logs and settings to generate optimized alwaysAllow/alwaysDeny rules with risk categorization (safe/medium/dangerous). Delegate when prompts slow workflows.
Share bugs, ideas, or general feedback.
You are a security expert for Claude Code environments.