critic-security

critic-security is a skill for Claude Code from iampawan/Manifest. It costs 36 tokens per session (654 once invoked), scanned A, original, MIT.

A security and privacy review skill for software-change contracts, covering login requirements, permissions, personal data, injection risks, and secrets.

In plain words
What is it for?
Use it to review authentication, authorization, ownership and tenant boundaries, personal-data handling, injection surfaces, and secret exposure before implementation.
Why use it?
It finds cases where a contract does not say who may use a behavior, whose data may be accessed, or how untrusted input and sensitive information are protected.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the manifest plugin — 28 skills, 15 commands shipped together

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.

agentmods
npx agentmods add skills/iampawan/manifest/critic-security
Any agent
npx skills add iampawan/Manifest --skill critic-security
Clone the repo
git clone --depth 1 https://github.com/iampawan/Manifest

Made for: Claude Code.

Or install manifest, the plugin that ships this one along with the rest of its 28 skills, 15 commands.

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 critic-security

README.md
[![agentmods](https://agentmods.dev/badge/skills/iampawan/manifest/critic-security.svg)](https://agentmods.dev/skills/iampawan/manifest/critic-security)
Your own site
<a href="https://agentmods.dev/skills/iampawan/manifest/critic-security"><img src="https://agentmods.dev/badge/skills/iampawan/manifest/critic-security.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 654 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00036 $0.00654
Opus 5 $0.00018 $0.00327
Sonnet 5 $0.00007 $0.00131
Haiku 4.5 $0.00004 $0.00065

Measured 5d ago against content hash 2c0297ede4aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

critic-security 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 5d 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/critic-security/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security critic

Protocol: Follow reference/CRITIC-RULES.md (the compact runtime rules) at the plugin root for severity definitions (the closed enum blocker/warning/info), the output JSON schema, ID prefixes, and shared anti-patterns. This skill defines only WHAT to look for. Do not invent severities like "high"/"medium" — the validator rejects them. Do not re-check anything the deterministic validator (scripts/validate.mjs) already covers; add the judgment layer on top.

You scan for what the contract doesn't say about who can do what, what data is exposed, and where adversarial input lands.

What to check

1. Authentication state

For each behavior, is it clear who can perform it? Flag any behavior that doesn't specify:

  • Anonymous vs logged-in
  • Required scope / permission level
  • What happens on auth failure

2. Authorization

If the behavior accesses or mutates a resource, is ownership clear?

  • Can a user access another user's data? When?
  • Are there admin / staff overrides?
  • Cross-tenant boundaries — if multi-tenant, what prevents tenant A from seeing tenant B's data?

3. PII and sensitive data

  • Does the behavior collect or display PII (email, phone, address, payment info, health data, etc.)?
  • Is the storage/transmission spec'd (encrypted at rest, TLS, masking)?
  • Does any analytics event include PII as a property? Flag — events should not carry raw PII.
  • For payment data: PCI scope considerations.

4. Input validation

For any user input the behavior accepts:

  • Length limits
  • Allowed character set / format
  • Rate limits to prevent abuse
  • Sanitization expectations (rendering as HTML? markdown?)

5. Injection / XSS surfaces

  • User-generated content displayed back to others — escaping rules?
  • URL parameters used in rendering — sanitization?
  • File uploads — type, size, scanning?

6. Secrets and configuration

  • New external services or API keys — where do they live?
  • Webhook endpoints — signature verification?
  • Third-party callbacks — replay protection?

Read the full file on GitHub · 89 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. 5d ago First seen · 89 lines · 36 tokens per session scan A 2c0297ede4aa

Subscribe to this mod's changes

critic-security is a skill published in the GitHub repository iampawan/Manifest (5 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 654 once invoked, about $0.0002 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 2026-08-31.

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

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens