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.
npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-cdn-traffic-anomaly-analysisgit clone --depth 1 https://github.com/huaweicloud/huaweicloud-skillsWrote 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.
[](https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cdn-traffic-anomaly-analysis)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cdn-traffic-anomaly-analysis"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cdn-traffic-anomaly-analysis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cdn-traffic-anomaly-analysis"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cdn-traffic-anomaly-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 161 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
- low Excessive Agency · line 141 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
- low Privilege Escalation · line 194 Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.Fix: Request only the minimum permissions required. Document why each permission is needed. Remove broad permissions like '*' or 'all'.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00176 | $0.03797 |
| Opus 5 | $0.00088 | $0.01899 |
| Sonnet 5 | $0.00035 | $0.00759 |
| Haiku 4.5 | $0.00018 | $0.00380 |
Grade B, and why
huawei-cloud-cdn-traffic-anomaly-analysis scanned grade B 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 12d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
> 1. **Stop immediately** - Do not execute any commands How it starts
The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CDN Traffic Anomaly Analysis
Overview
This skill analyzes CDN domain traffic anomalies by querying billing mode and corresponding traffic/bandwidth metrics. It automatically determines the appropriate metric based on the account's billing mode (bw_95, flux, combine_flux, bw, bw_peak), queries historical data over a configurable time range, establishes a 3-month baseline for comparison, and identifies potential traffic theft or abuse using both absolute thresholds and relative baseline deviation.
Key Features:
- Automatic billing mode detection and metric selection
- Support for all billing modes: bw_95, flux, combine_flux, bw, bw_peak
- Domain validation and traffic analysis
- 3-month baseline analysis — detects relative traffic surges against historical norms
- Dual-threshold anomaly detection — absolute thresholds + relative baseline comparison
- Three-tier conclusions: Normal / Watch (relative surge) / Anomalous (absolute threshold exceeded)
- Comprehensive analysis reports with baseline comparison and daily breakdowns
Tool: hcloud CLI (KooCLI)
Timestamp Tool: scripts/cdn_timestamp.py (built-in)
Analysis Scope: Past 7 days for current window (configurable); past 3 months for baseline
Core Principle: Query only the metric corresponding to the billing mode; use API capabilities efficiently to cover both current and baseline windows with minimal API calls
⛔ Prohibited Operations (Security Constraints)
This skill strictly forbids the following operations, regardless of user requests:
| Prohibited Operation | API/Command | Reason |
|---|---|---|
| ❌ Modify domain configuration | ModifyDomainConfig / hcloud CDN UpdateDomain |
Write operation; may affect production traffic |
| ❌ Delete domain | DeleteDomain / hcloud CDN DeleteDomain |
Irreversible; removes domain from CDN |
| ❌ Disable domain acceleration | DisableDomain / hcloud CDN DisableDomain |
Affects production traffic |
| ❌ Modify billing mode | UpdateBillingMode |
Financial impact; requires explicit authorization |
What ships with it
14 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.
- references/acceptance-criteria.md 2.5 KB
- references/cli-installation-guide.md 823 B
- references/dataflow-diagram.md 4.1 KB
- references/iam-policies.md 908 B
- references/related-apis.md 1.7 KB
- references/task-domain-validation.md 906 B
- references/task-list-domains.md 633 B
- references/task-query-metrics.md 5.0 KB
- references/task-show-charge-modes.md 1.0 KB
- references/task-threshold-judgment.md 5.6 KB
- references/task-timestamp-calculation.md 1.8 KB
- references/troubleshooting.md 4.1 KB
- references/verification-method.md 2.2 KB
- scripts/cdn_timestamp.py 4.1 KB runs code
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.
- 12d ago First seen · 323 lines · 176 tokens per session scan B a669a0e7f200
huawei-cloud-cdn-traffic-anomaly-analysis is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (49 stars, last pushed yesterday), licensed MIT. It adds 176 tokens to every session and 3,797 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
arvancloud-api
Operate ArvanCloud (arvancloud.ir) APIs — CDN, DNS records, Cloud Server / IaaS, Object Storage, Edge Computing, Cloud Container (CaaS), VOD/Live/Video Ads — and issue Let's Encrypt wildcard TLS certificates via acme.sh's dnsarvan plugin. Use this whenever the user wants to manage anything on ArvanCloud — listing…
hetzner
Use when provisioning or hardening a Hetzner Cloud VPS: picking the plan/location (CX/CPX/CAX/CCX), bringing it up reproducibly with hcloud + cloud-init, locking down SSH, and wiring the Cloud Firewall to hand off a Docker-ready host. NOT app deploys on Coolify (that is coolify), NOT Dockerfiles (that is docker), NOT…
cloudflare-expert
Expert-level Cloudflare Workers, CDN, edge computing, and security services. Use when the user mentions edge computing, CDN, workers, or WAF, or when the task involves Cloudflare Services or Developer Tools.
edge-computing-expert
Design and implement production-grade edge computing solutions including CDN optimization, fog computing architectures, and distributed edge workloads. Use when the user mentions edge computing, CDN or edge caching, fog computing, MEC, IoT edge workloads, or latency-sensitive distributed deployments.
cloudflare-dns
Manage Cloudflare DNS records, proxy status, TTLs, and API tokens while planning and verifying DNS changes.
image-optimization-cdn
Speed up your store by automatically resizing and converting product images to WebP/AVIF, adding lazy loading, and serving via CDN.