h0p3sf4ll

AI Security Review — Security skill for Claude Code

Security community

Review AI/LLM prompt, retrieval, memory, tool/agent authority, tenant isolation, output sinks, and provider data boundaries.

How to install AI Security Review

Installs to ~/.claude/commands/h0p3sf4ll-threatlint-ai-security-review.md

Terminal
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/h0p3sf4ll/threatlint/HEAD/.claude/commands/ai-security-review.md -o ~/.claude/commands/h0p3sf4ll-threatlint-ai-security-review.md

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

What AI Security Review does

description: "Review AI/LLM prompt, retrieval, memory, tool/agent authority, tenant isolation, output sinks, and provider data boundaries." argument-hint: "Optional AI flow, tool, retrieval pipeline, component, or redacted evidence path"

Delegate to `appsec-ai-security-reviewer`. Pass `$ARGUMENTS` as the scope and supplied evidence locations.

Load `threatlint-evidence-analysis`, `threatlint-actionable-reporting`, then `threatlint-ai-security`. Trace untrusted inputs through models/retr

Alternatives in Security

  • Token Scan — Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP l 3.8k ★
  • Promptmap — Security scanner for custom LLM apps 1.2k ★
  • Review Artifact — Creates one polished, self-contained HTML artifact from review findings, audit notes, PR feedback, code review 652 ★

Full documentation available on GitHub

View Source Repository

Related Skills

LLM — Security skill for Claude Code

LLM

Security review of AI/LLM features — prompt injection, agent tool authority, RAG poisoning, and unsafe model o

Security community
Peon Mem — Security skill for Claude Code

Peon Mem

Local-first hierarchical memory brain for AI coding agents — auto-capture, LLM consolidation, hybrid retrieval

Security community
Audit Tenancy — Security skill for Claude Code

Audit Tenancy

Audit multi-tenancy enforcement — RLS policies, withTenantDb usage, query-time tenant filters, and cross-tenan

Security community
LLM Security — Security skill for Claude Code

LLM Security

AI/LLM agent security audit (OWASP GenAI/LLM Top 10 2026): prompt injection (direct + indirect/RAG), jailbreak

Security community
Secure LLM Gateway — Security skill for Claude Code

Secure LLM Gateway

Security-focused gateway in front of an LLM API — auth, prompt-injection defense, output filtering, audit logg

Security community
LLM Memory Audit Prompts — Security skill for Claude Code

LLM Memory Audit Prompts

Audit Your LLM Memory: Prompt Recipes for Business Users

Security community

Related Agents

Appsec AI Security Reviewer — Security agent for Claude Code

Appsec AI Security Reviewer

Use for AI/LLM application security review: direct/indirect prompt injection, tool and agent authorization, RA

Security community
LLM Sec Review — Security agent for Claude Code

LLM Sec Review

LLM/agent security review specialist — prompt injection, the Agents Rule of Two, tool-call authorization, mode

Security community
Nadia Security Auditor — Security agent for Claude Code

Nadia Security Auditor

Use for adversarial security review - authentication and authorization patterns, multi-tenant data isolation,

Security community