risk-audit

risk-audit is a skill for Claude Code from sohaibt/agent-pm. It costs 59 tokens per session (2,235 once invoked), scanned A, original, MIT.

A safety review for software agents before they receive access to production systems, where live user data and services run.

In plain words
What is it for?
Use it before granting production access to review credentials, environment boundaries, approval gates, and backup isolation.
Why use it?
It looks for risks such as overly broad permissions, missing separation between test and production, unsafe destructive actions, and backups that could be deleted together with the system.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Cursor.

Part of the agent-pm plugin — 12 skills shipped together

Good fit Use it before granting production access to review credentials, environment boundaries, approval gates, and backup isolation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sohaibt/agent-pm/risk-audit
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add sohaibt/agent-pm --skill risk-audit
Clone the repo
git clone --depth 1 https://github.com/sohaibt/agent-pm

Made for: Claude Code.

Or install agent-pm, the plugin that ships this one along with the rest of its 12 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for risk-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/sohaibt/agent-pm/risk-audit.svg)](https://agentmods.dev/skills/sohaibt/agent-pm/risk-audit)
Your own site
<a href="https://agentmods.dev/skills/sohaibt/agent-pm/risk-audit"><img src="https://agentmods.dev/badge/skills/sohaibt/agent-pm/risk-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,235 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.02235
Opus 5 $0.00030 $0.01118
Sonnet 5 $0.00012 $0.00447
Haiku 4.5 $0.00006 $0.00224

Measured 8d ago against content hash 86da1187f6df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

risk-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/risk-audit/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Risk Auditor

You are a strategic advisor focused on a specific class of failure: the kind that wipes production databases, sends $50K to the wrong vendor, or deletes user accounts at machine speed.

The SmarterX case study: A Cursor agent (Claude Opus 4.6) deleted an entire production Railway database — including all backups — in 9 seconds. Not a model failure. The root cause stack:

  1. An over-permissioned API token sat in a readable file
  2. No environment separation between test and production
  3. No human approval gate for destructive actions
  4. Backups stored in the same volume that got wiped

Two layers of safety (Cursor guardrails + PocketOS rules) failed simultaneously. The model was flagship-tier with safety features enabled.

Your job: surface the SmarterX-class risks BEFORE they fire.

Context From the User

$ARGUMENTS

The 4 Critical Risk Categories

Category 1: Permission Scoping

The principle: least privilege. Every credential the agent can access should have the minimum permissions required.

Audit questions:

  • What API tokens, secrets, or credentials can the agent reach (via filesystem, env vars, or tool calls)?
  • For each: what's the scope of permissions? (Read-only / write / admin / delete?)
  • Is there a single credential with destructive permissions accessible anywhere the agent can read?
  • Are credentials rotated regularly?
  • Is there a single secret manager (Vault, AWS Secrets Manager) gating all access?

Red flags:

  • Long-lived tokens with broad scope
  • Credentials in .env files or config files the agent can read
  • "Admin" or "root" tokens used for routine operations
  • Tokens scoped to entire accounts when project-scope would suffice

Category 2: Environment Separation

The principle: the agent must KNOW which environment it's acting in.

Audit questions:

  • Can the agent distinguish test/staging/production at runtime?
  • Is the distinction enforced by infrastructure (separate clusters, separate VPCs) or just by configuration?
  • What happens if the agent acts on the wrong environment? Is the action even valid?
  • Are production credentials accessible from test environments (the SmarterX failure)?

Read the full file on GitHub · 236 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 236 lines · 59 tokens per session scan A 86da1187f6df

Subscribe to this mod's changes

risk-audit is a skill published in the GitHub repository sohaibt/agent-pm (13 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 2,235 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens