Security plugins

Redacts API keys, tokens and private keys from tool results before Claude reads them, and refuses writes and commands that embed one.

Stops credential-shaped strings and a private deny-list of words from being written into files or shell commands, by Claude or by any subagent.

Security guardrail for git: blocks Claude's commits and pushes that skip pre-commit hooks or signing (--no-verify, --no-gpg-sign, commit.gpgsign=false), so your hooks, linters and commit signing always run.

Blocks agent package installs that are too fresh, too obscure, typosquats, or add install scripts.

Blocks destructive shell commands (rm -rf outside the project, force-push to main, DROP DATABASE) and snapshots uncommitted work before risky git commands.

Defence-in-depth advisories for destructive commands, attribution, and remote execution.

Hides the secrets you paste before Claude or the transcript sees them, stores them per project in the macOS Keychain, and exports them to Bash as environment variables. Optional PII hiding.

Local deterministic pattern bridge for new file content. Not the official Claude Security plugin and not a data-flow scanner.

Appends architecture rules as Claude-only context on every prompt, and drops prompts that explicitly tell Claude to ignore or bypass security rules.

Default-closed eval gate. External Promptfoo runs in CI are the real gate; this mod is defence in depth only.

817 cybersecurity skills covering web security, pentesting, DFIR, threat intelligence, cloud security, malware analysis, and more. Mapped to 6 frameworks.

200 skills

817 cybersecurity skills covering web security, pentesting, DFIR, threat intelligence, cloud security, malware analysis, and more. Mapped to 6 frameworks.

200 skills

817 cybersecurity skills (pentest, DFIR, threat-intel, cloud, malware, incident response) mapped to 6 frameworks (MITRE ATT&CK, NIST CSF, ATLAS, D3FEND, AI RMF, F3), from mukul975/Anthropic-Cybersecurity-Skills. Authorized/lawful use only - includes dual-use offensive techniques.

200 skills

83-skill bug-hunting & external red-team bundle — 58 hunt-* web/vuln-class + framework skills, enterprise platform attack chains (M365/Entra, Okta, SharePoint, vCenter, SSL-VPN, APK/iOS), recon/OSINT, reporting & validation gates, Burp MCP integration. Skills auto-load by topic; 15 slash commands.

83 skills · 15 commands

71-skill bug-hunting & external red-team bundle — 48 hunt-* web/vuln-class + framework skills, enterprise platform attack chains (M365/Entra, Okta, SharePoint, vCenter, SSL-VPN, APK), recon/OSINT, reporting & validation gates, Burp MCP integration. Skills auto-load by topic; 15 slash commands.

71 skills · 14 commands

Curated cybersecurity audit skills focused on mobile, Tauri desktop, web/webview, REST/JWT/OAuth APIs, Postgres/SQLi, Edge Functions, crypto, SAST/DAST/SCA, and threat modeling.

68 skills

Manage Zscaler cloud security platform including ZPA (private access), ZIA (internet access), ZDX (digital experience), ZCC (client connector), EASM (attack surface), and Z-Insights (analytics). Create and manage policies, troubleshoot connectivity, audit security configurations, and investigate incidents across the full Zscaler ecosystem.

42 skills · 20 commands · 1 MCP server

Manage Zscaler cloud security platform including ZPA (private access), ZIA (internet access), ZDX (digital experience), ZCC (client connector), EASM (attack surface), and Z-Insights (analytics). Create and manage policies, troubleshoot connectivity, audit security configurations, and investigate incidents across the full Zscaler ecosystem.

42 skills · 20 commands · 1 MCP server

Skills for the defensive side of shipping software: review a change for the vulnerability classes that actually get exploited, reduce who can do what toward least privilege without breaking production, rotate or contain a credential, harden a container image and keep checking it, read a Terraform plan for what it destroys, preserve evidence and build an intrusion timeline after a compromise, respond to credential stuffing, write and test detection rules, prove tenant isolation, handle vulnerability reports from outside researchers, and reverse engineer the binaries, managed CIL assemblies, APK packages, packaged apps, firmware and WebAssembly you are authorised to examine — including de-bloating a smart-TV or streaming device you own.

31 skills · 2 commands · 5 agents

Passive external attack-surface mapping: CT subdomains, DNS, TLS, HTTP posture, RDAP/WHOIS, Shodan via MCP. STDIO or Streamable HTTP.

35 skills · 1 MCP server

CISA Known Exploited Vulnerabilities with BOD 26-04 deadlines, SSVC prioritization, and the full ICS advisory corpus (CSAF) via MCP. Keyless. STDIO or Streamable HTTP.

35 skills · 1 MCP server

Search and audit CVEs by keyword, severity, CWE, CISA KEV status, and CPE via the NIST National Vulnerability Database. STDIO or Streamable HTTP.

35 skills · 1 MCP server

AI Security Harness for Claude Code: scans the code Claude writes as it writes it and feeds findings back so they are fixed before the turn moves on.

17 skills · 5 commands · 8 agents · 1 MCP server · hooks

One guided entry for readiness, security checks, result review and same-state retesting with developer/QA/PM reports.

22 skills · 7 commands

Detection skills for opentide repositories. Agents model threats, define what to detect, and write the rules and queries, with the platform and internals context each detection depends on.

28 skills

Duende development skills and agents for Claude Code — covering OAuth/OIDC protocols, IdentityServer, token management, ASP.NET Core authentication/authorization, BFF patterns, and secure identity architecture

24 skills · 2 agents

Duende development skills and agents for Claude Code — covering OAuth/OIDC protocols, IdentityServer, token management, ASP.NET Core authentication/authorization, BFF patterns, and secure identity architecture

24 skills · 2 agents

Duende development skills and agents for Claude Code — covering OAuth/OIDC protocols, IdentityServer, token management, ASP.NET Core authentication/authorization, BFF patterns, and secure identity architecture

24 skills · 2 agents

Chain-of-custody evidence handling — hash, timestamp, inspect metadata, append to an immutable custody register, package as BagIt, verify, and sync to WORM or S3 Object Lock storage.

14 skills · 12 commands

Duende development skills and agents for Claude Code — covering OAuth/OIDC protocols, IdentityServer, token management, ASP.NET Core authentication/authorization, BFF patterns, and secure identity architecture

24 skills · 2 agents