Drix10

Audit Risk — Security skill for Claude Code

Security community

Find new risk surfaces (dependencies, auth, payments, destructive data ops, outbound calls, secrets) since the baseline.

How to install Audit Risk

Installs to ~/.claude/skills/drix10-agent-flow-audit-risk/SKILL.md

Terminal
mkdir -p ~/.claude/skills/drix10-agent-flow-audit-risk && curl -fsSL https://raw.githubusercontent.com/Drix10/agent-flow/HEAD/prompts/audit-risk.md -o ~/.claude/skills/drix10-agent-flow-audit-risk/SKILL.md

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

What Audit Risk does

description: Find new risk surfaces (dependencies, auth, payments, destructive data ops, outbound calls, secrets) since the baseline

Follow the `gardener` skill's /audit-risk procedure: call `risk_audit`, group new surfaces by type, propose protected_paths / risk_boundaries updates, and call `risk_baseline_update` with only the keys I accept. Secrets are never accepted — tell me to remove and rotate them.

Alternatives in Security

  • ThinkWatch — Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII 817 ★
  • Perplexity Super Skills — Complete collection of 12 Perplexity Computer Super-Skills merging Perplexity + Claude Code capabilities acros 346 ★
  • Openclaw Ops — OpenClaw operations skill with health checks, repair scripts, watchdogs, update triage, and security scans 225 ★

Full documentation available on GitHub

View Source Repository

Related Skills

Migration Audit — Security skill for Claude Code

Migration Audit

Safety review of pending Supabase / Postgres migrations: destructive ops, locking impact on large tables, miss

Security community
Sieve — Security skill for Claude Code

Sieve

A fully local LLM-traffic security proxy for crypto-native developers — redacts secrets outbound, blocks dange

Security community
My Security Review — Security skill for Claude Code

My Security Review

Run a personal agent-tooling security review - secrets, shell/hook command execution, untrusted input, plugin/

Security community
Branch Audit — Security skill for Claude Code

Branch Audit

Read-only audit of local branches, worktrees, and PR state. Classifies each as fully-merged / unique-work / st

Security community
Redstamp — Security skill for Claude Code

Redstamp

own your agent security — a deterministic, offline firewall for AI agent tool calls. Blocks secret exfil, prom

Security community
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

Related Agents

Web Security — Security agent for Claude Code

Web Security

Website security reviewer. Use before shipping, or after touching auth, payments, webhooks, uploads, database

Security community
Security Advisor — Security agent for Claude Code

Security Advisor

Read-only security reviewer for auth, authz, payments, RLS, secrets, PII, and deletion. Writes every finding i

Security community
Noctis — Security agent for Claude Code

Noctis

Use once per PR-ready point on a diff that touches auth, sessions, payments or in-app purchases, admin, upload

Security community