prototype-pollution

prototype-pollution is a skill for Claude Code from ByamB4/find-cve-agent. It costs 29 tokens per session (791 once invoked), scanned A, original, Apache-2.0.

A security checker for prototype pollution, where attacker-controlled object keys change shared JavaScript object properties such as Object.prototype.

In plain words
What is it for?
Use it to audit merge, clone, deep-assignment, query-string, JSON, and configuration utilities that recursively copy properties from untrusted objects.
Why use it?
It helps verify both the unsafe property-setting path and a real security impact, instead of treating any occurrence of keys like __proto__ as a confirmed vulnerability.

Skill for Claude Code

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

Part of the find-cve-agent plugin — 21 skills, 7 commands, 5 agents 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/byamb4/find-cve-agent/prototype-pollution
Any agent
npx skills add ByamB4/find-cve-agent --skill prototype-pollution
Clone the repo
git clone --depth 1 https://github.com/ByamB4/find-cve-agent

Made for: Claude Code.

Or install find-cve-agent, the plugin that ships this one along with the rest of its 21 skills, 7 commands, 5 agents.

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 prototype-pollution

README.md
[![agentmods](https://agentmods.dev/badge/skills/byamb4/find-cve-agent/prototype-pollution.svg)](https://agentmods.dev/skills/byamb4/find-cve-agent/prototype-pollution)
Your own site
<a href="https://agentmods.dev/skills/byamb4/find-cve-agent/prototype-pollution"><img src="https://agentmods.dev/badge/skills/byamb4/find-cve-agent/prototype-pollution.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 791 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 $0.00029 $0.00791
Opus 5 $0.00015 $0.00396
Sonnet 5 $0.00006 $0.00158
Haiku 4.5 $0.00003 $0.00079

Measured 6d ago against content hash e535d7440ac6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

prototype-pollution 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 6d 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/prototype-pollution/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.

Prototype Pollution Detection

When to Use

Audit merge/clone/deep-assign utilities, query string parsers, JSON parsers, config mergers, and any package that recursively sets object properties from untrusted input.

Key insight: Only ~50% acceptance rate. Must demonstrate REAL impact beyond just polluting prototype.

Process

Step 1: Find Object Manipulation Sinks

grep -rn "Object\.assign\|Object\.defineProperty\|Object\.create" .
grep -rn "merge\|extend\|deepMerge\|deepExtend\|deepAssign\|mixin" .
grep -rn "clone\|deepClone\|cloneDeep\|deepCopy" .
grep -rn "set\|setPath\|setValue\|lodash\.set\|_.set" .
grep -rn "\[.*\]\s*=" . --include="*.js"  # Bracket notation assignment

Step 2: Check for Recursive Property Setting

Look for patterns where object keys from user input are used as property paths:

// VULNERABLE: recursive merge without key filtering
function merge(target, source) {
  for (const key in source) {
    if (typeof source[key] === 'object') {
      target[key] = merge(target[key] || {}, source[key]);
    } else {
      target[key] = source[key];
    }
  }
}

Step 3: Check Key Filtering

grep -rn "__proto__\|constructor\|prototype" . | grep -i "filter\|block\|skip\|ignore\|reject"
grep -rn "Object\.create(null)" .  # Null prototype objects are safe
grep -rn "hasOwnProperty\|Object\.keys\|Object\.entries" .

Step 4: Assess Impact

Prototype pollution alone is often not enough. Look for impact:

  • DoS: Polluted property causes TypeError crash (toString, valueOf)
  • Property injection: Polluted property affects security logic (isAdmin, role, auth)
  • Gadget chains: Polluted property reaches dangerous sink (eval, template)
  • Method clobbering: toString/valueOf overwritten causing crash

Dangerous Keys

Key Effect Impact
__proto__ Sets properties on Object.prototype All objects affected
constructor.prototype Same effect via constructor chain All objects affected
constructor Overwrites constructor reference Type confusion
toString Overwrites string conversion TypeError on string operations
valueOf Overwrites value conversion TypeError on comparisons
hasOwnProperty Overwrites property check Logic bypass

Read the full file on GitHub · 89 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 89 lines · 29 tokens per session scan A e535d7440ac6

Subscribe to this mod's changes

prototype-pollution is a skill published in the GitHub repository ByamB4/find-cve-agent (47 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 791 once invoked, about $0.0001 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

wordpress-plugin-hunt

Hunt WP plugins via REST, exploit CVEs when version known.

uphiago/recon-skills · 19 tokens

deep-invade

Deep pentest WP: SSRF, plugin CVE, JS mine, port scan chain.

uphiago/recon-skills · 24 tokens

wp-plugin-cve-hunt

Systematic approach to finding and testing CVEs for identified WordPress plugins. Covers plugin discovery, version extraction from multiple sources (readme.txt, assets, inline JS), CVE database cross-referencing with WPScan/Patchstack/NVD/NVD API, version-based vulnerability matching, exploitation PoC generation, and…

uphiago/recon-skills · 160 tokens

bug-bounty-hunting

Hunt vulnerabilities like an expert, not a linear software engineer: come at a target from the overlooked angle, reason by analogy and transfer proven attack mechanisms, attack the hidden assumptions and the seams between systems, drill to the mechanism, then keep it honest with proof and persistence (acceptance !=…

rozetyp/vuln-intel-mcp · 263 tokens

create-site

Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…

microsoft/power-platform-skills · 73 tokens

google-ads-audit

Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…

nowork-studio/notfair-plugin · 114 tokens