Cloudflare applications can accumulate usage charges through retries, recurring jobs, and unbounded work. This skill reviews local configuration and source for supported cost mechanisms and uncertainties.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "daftai-cloudflare-billing-audit" from https://skillstore.io/skills/daftai2026-daftai-cloudflare-billing-audit.md and its manifest at https://skillstore.io/api/skills/daftai2026-daftai-cloudflare-billing-audit/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.
Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
All 400 supplied matches were adjudicated as false positives from exclusions, synthetic tests, documentation, or bounded offline operations. No evidence found for credential exfiltration, malicious execution, or prompt injection in the reviewed context. The analyzer omitted 238 additional matches; manual review remains required, and portable filesystem access requires stable input and output trees. Static review was capped at 400/638 representative findings; omitted static matches are unconfirmed, so automatic publishing stays disabled until manual review.
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
daftai2026. (2026). daftai-cloudflare-billing-audit security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/daftai2026-daftai-cloudflare-billing-audit/audits/1
BibTeX citation
@techreport{daftai2026-daftai2026-daftai-cloudflare-billing-audit-2026,
author = {daftai2026},
title = {daftai-cloudflare-billing-audit security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/daftai2026-daftai-cloudflare-billing-audit/audits/1},
note = {Author version unspecified}
}
CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "daftai-cloudflare-billing-audit security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "daftai2026"
date-released: "2026-10-13"
url: "https://skillstore.io/skills/daftai2026-daftai-cloudflare-billing-audit/audits/1"
identifiers:
- type: other
value: "skillstore:daftai2026-daftai-cloudflare-billing-audit:audit:1"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this scoreEvidence Confidence: Medium
68
Architecture
85
Maintainability
87
Content
65
Community
91
Spec Compliance
What You Can Build
Review a Worker before release
Inspect configured request paths and recurring jobs for source-supported cost amplification before deployment.
Investigate queue and alarm exposure
Trace queue feedback, retries, and Durable Object scheduling while distinguishing persistent job limits from per-invocation controls.
Prepare a cost-risk review
Summarize supported mechanisms, coverage gaps, and owner verification steps without requiring credentials or assuming production usage.
Try These Prompts
Start an offline audit
Audit the Cloudflare project at [absolute project path] for billing exposure. Keep the review offline and read-only, and separate supported findings from unknowns.
Focus on one workspace
Audit [absolute workspace path] for Workers and D1 cost mechanisms. Review configured entry points, query amplification, and listed migrations. Record deployment and index uncertainty.
Trace recurring work
Review [absolute project path] for queue feedback and Durable Object alarm recurrence. Trace persistent job budgets, progress, retries, and terminal guards through fingerprint-checked evidence.
Model a bounded cost scenario
Audit [absolute project path] and estimate costs using [plan, period, currency, and supplied usage assumptions]. Retrieve current official pricing and record dates, units, and uncertainties.
Best Practices
Provide an explicit project path and a private output location outside the target tree; keep target, ancestor, and output trees stable.
Review only fingerprint-checked evidence and inspect actual triggers, guards, and persistent limits before promoting a scanner candidate.
Keep traffic assumptions, deployment uncertainty, and pricing dates explicit; use current official pricing only for requested estimates.
Avoid
Treating an empty candidate list or a binding declaration as proof of safety or proof of a billing defect.
Running target scripts, reading excluded credential files, or bypassing a refused controlled read with another reader.
Presenting budget alerts, per-request limits, or stale pricing as a guaranteed whole-account spending cap.
Frequently Asked Questions
Which assistants can use this skill?
The skill supports Claude, Codex, and Claude Code. Its helper requires Bun and a supported local filesystem environment.
Does the audit require a Cloudflare token?
No. Default audits inspect local files offline and do not sign in, call account APIs, or read credentials.
Does it run or modify my application?
No. It does not execute target code, scripts, tests, hooks, or migrations. Reports are written outside the target tree.
Can it prevent an unexpected bill?
No. It identifies supported exposure mechanisms and review gaps. It does not enforce account limits or guarantee a spending cap.
Are all Cloudflare products scanned automatically?
No. Automated candidates cover narrow alarm and queue patterns. Product guides support broader agent review of authorized evidence.
Can it estimate monthly charges?
Only when explicitly requested. Estimates require current official prices, plan details, billing period, currency, usage assumptions, and stated uncertainties.