Security plugins

Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns

hooks

Evidence-based application security review skill and portable reviewer agent.

1 skill

Security review guidance for LLM, agent, RAG, and tool-calling systems.

1 skill

GitHub CodeQL configuration and troubleshooting guidance.

1 skill

Comprehensive security audit of repositories — OWASP Top 10, CWE Top 25, secrets detection, injection vectors, auth/authz flaws, dependency CVEs, infrastructure misconfigurations

1 skill

Opt-in Semgrep SAST extension (separate trust model); shells to an external semgrep if installed and never touches the auditor's zero-dependency core. Off by default.

1 command

Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.

hooks

Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns

hooks

Evidence-backed security audits with optional Jev review.

1 skill

Meta-dispatcher for the redcap suite. Routes red-team and device-research intent to the appropriate sibling skill. Start here when the right sibling isn't obvious or when a task needs multiple siblings chained.

1 skill

Offensive payload library lookup. SQL injection, XSS, SSTI, LDAP, XXE, CSRF, CRLF, SSRF, deserialization, auth bypass, WAF bypass, CVE-specific exploits. Thin wrapper around a local clone of swisskyrepo/PayloadsAllTheThings with topic-folder navigation and Intruder wordlist retrieval.

1 skill

Handles web pages, files, tool output, and inter-agent messages as data rather than instructions, with injection triage and a bounded escalation path.

1 skill

Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns

hooks

Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns

hooks

Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns

hooks

Security guidance and review for code changes.

hooks

3-stage security audit with parallel attacker agents.

1 skill

Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns

hooks

Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns

hooks

Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns

hooks

Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns

hooks

Security reminder hook that warns about potential security issues when editing files

hooks

Screens inbound prompts through a local Little Canary service before the host sends them to the main model.

hooks

Jailbreak regression benchmark for LLM endpoints with repeatable known-pattern attacks and deterministic scoring.

1 skill

Security audit and vulnerability scanner for AI agent skills. Scans for malicious code, prompt injection, data exfiltration, supply chain risks, and privilege escalation before installation. Zero dependencies, PASS/WARN/FAIL verdicts with remediation guidance.

1 skill

Security audit and vulnerability scanner for AI agent skills. Scans for malicious code, prompt injection, data exfiltration, supply chain risks, and privilege escalation before installation. Zero dependencies, PASS/WARN/FAIL verdicts with remediation guidance.

1 skill

Screens inbound prompts through a local Little Canary service before the host sends them to the main model.

hooks

Jailbreak regression benchmark for LLM endpoints with repeatable known-pattern attacks and deterministic scoring.

1 skill

Security best practices and vulnerability detection

hooks

Warn about potential security issues when editing files - targets command injection, XSS vulnerabilities, and dangerous coding patterns

hooks