buvis

Mallory — Security agent for Claude Code

Security community

Security-lens reviewer, armed only when the diff trips the security trigger.

How to install Mallory

Installs to ~/.claude/agents/buvis-claude-autopilot-mallory.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/buvis/claude-autopilot/HEAD/agents/mallory.md -o ~/.claude/agents/buvis-claude-autopilot-mallory.md

Restart Claude Code, or start a new session, for it to be picked up.

What Mallory does

name: mallory description: Security-lens reviewer, armed only when the diff trips the security trigger. Checks secrets, injection, authz, logging. tools: Read

You are the SECURITY reviewer of a completed change. Review ONLY through the security lens.

Checklist:

  • No hardcoded secrets.
  • Input validated and sanitized at every boundary.
  • No SQL or command injection risk.
  • Auth/authz correctly applied.
  • Sensitive data never logged.

Report only defects you can ground in the diff above.

Alternatives in Security

Full documentation available on GitHub

View Source Repository

Related Agents

Lens Security — Security agent for Claude Code

Lens Security

Security lens of the production readiness audit. Attacks the codebase on paper - injection, SSRF, path travers

Security community
Harness Security Reviewer — Security agent for Claude Code

Harness Security Reviewer

Security reviewer — self-scoping OWASP Top 10 and STRIDE audit of a pinned diff, covering auth, secrets, input

Security community
Psychodrama Security — Security agent for Claude Code

Psychodrama Security

Use ONLY by psychodrama-protocol skill orchestrator. Evaluates theses through threat model / attack surface /

Security community
Critic Security — Security agent for Claude Code

Critic Security

Review code for OWASP-style security issues (injection, authn/authz, secrets, supply chain, LLM-specific) in p

Security community
Security Critic — Security agent for Claude Code

Security Critic

Adversarially reviews a code change through the single SECURITY lens (rubric lens 3) and emits a critic-schema

Security community
Cybersecurity Expert — Security agent for Claude Code

Cybersecurity Expert

Threat-models code and architecture changes across trust boundaries, authn/authz flows, secrets handling, and

Security community

Related Skills

Vibe Secure — Security skill for Claude Code

Vibe Secure

Security audit for AI-generated code. Catches hardcoded secrets, injection surfaces, auth gaps, and insecure d

Security community
AegisGate — Security skill for Claude Code

AegisGate

Open-source security gateway for LLM APIs — prompt injection detection, PII redaction, dangerous response sani

Security community
Sec Triage Agent — Security skill for Claude Code

Sec Triage Agent

Autonomous LLM security triage agent built with Python, Claude Code, Ollama, and Pydantic. Automatically parse

Security community