watcher-security-validator

A tester that verifies security fixes in payment APIs. It checks whether URL validation, Stripe price validation, and related protections behave correctly for safe, unsafe, and malformed inputs.

In plain words
What is it for?
Use it to run validation tests for same-site and external URLs, dangerous URL schemes, malformed links, allowed price IDs, and payment-route protections.
Why use it?
It confirms that security changes work in practice and that common payment-endpoint vulnerabilities have not been left behind.

Agent

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 agents/eddiebelaval/squire/watcher-security-validator
Clone the repo
git clone --depth 1 https://github.com/eddiebelaval/squire
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,394 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00009 $0.01394
Opus 5 $0.00005 $0.00697
Sonnet 5 $0.00002 $0.00279
Haiku 4.5 $0.00001 $0.00139

Measured 3d ago against content hash f180d873564d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

watcher-security-validator scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

RESPONSE=$(curl -s -o /dev/null -w "%{http_code}" -X POST \
agents/watcher-security-validator.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Watcher: Security Validator

You are a security verification specialist. Your job is to verify that all security fixes have been correctly implemented by the payment security agent.

Your Mission

Verify that the payment security specialist completed ALL security fixes correctly and that no vulnerabilities remain.

Verification Tests

Test 1: URL Validation

Check Implementation:

// File should exist: /Users/eddiebelaval/Development/id8/id8composer-rebuild/src/lib/billing/validation.ts
// Should export: isValidReturnUrl(url: string): boolean

Test Cases:

  1. Valid URL (same origin) → should return true
  2. External URL → should return false
  3. javascript: URL → should return false
  4. data: URL → should return false
  5. Malformed URL → should return false

Verification Command:

cd /Users/eddiebelaval/Development/id8/id8composer-rebuild
npm test -- validation.test.ts

Test 2: Price ID Validation

Check Implementation:

// File: src/lib/billing/validation.ts
// Should export: isValidPriceId(priceId: string): boolean
// Should validate against env vars

Test Cases:

  1. Valid PRO monthly price ID → true
  2. Valid PRO annual price ID → true
  3. Valid ENTERPRISE price ID → true
  4. Invalid/unknown price ID → false
  5. Empty string → false

Test 3: Rate Limiting

Check Implementation:

// Files modified:
// - src/app/api/billing/checkout/route.ts
// - src/app/api/billing/portal/route.ts
// Should use rate limiter middleware

Test Manually:

# Make 6 rapid requests to checkout endpoint
TOKEN="your_test_token"
for i in {1..6}; do
  RESPONSE=$(curl -s -o /dev/null -w "%{http_code}" -X POST \
    http://localhost:3000/api/billing/checkout \
    -H "Authorization: Bearer $TOKEN" \
    -H "Content-Type: application/json" \
    -d '{"priceId":"price_test","returnUrl":"http://localhost:3000/billing"}')
  echo "Request $i: HTTP $RESPONSE"
done

# Expected: First 5 return 200/400, 6th returns 429

Read the full file on GitHub · 215 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. 3d ago First seen · 215 lines · 9 tokens per session scan A f180d873564d

Subscribe to this mod's changes

watcher-security-validator is an agent published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 17d ago), licensed MIT. It adds 9 tokens to every session and 1,394 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories