Borrowing it
Nothing to install: this file belongs to robconery/cassini-workshop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/robconery/cassini-workshop/main/.claude/skills/security-web/SKILL.mdgit clone --depth 1 https://github.com/robconery/cassini-workshopWrote 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/robconery/cassini-workshop/security-web)<a href="https://agentmods.dev/skills/robconery/cassini-workshop/security-web"><img src="https://agentmods.dev/badge/skills/robconery/cassini-workshop/security-web/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/robconery/cassini-workshop/security-web"><img src="https://agentmods.dev/badge/skills/robconery/cassini-workshop/security-web.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00207 | $0.03019 |
| Opus 5.5 | $0.00083 | $0.01208 |
| Sonnet 5.5 | $0.00041 | $0.00604 |
| Haiku 4.5 | $0.00021 | $0.00302 |
Grade A, and why
security-web 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 2mo 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.
This is a copy
100% identical to security-web — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Application Security Review
Treat every byte that crossed a network boundary as hostile until proven
otherwise, and prove it on the server. The client is an untrusted rendering
surface you do not control. Frameworks add convenience (Server Actions,
Nitro routes, Bun.serve, Hono middleware) that hides the trust boundary
— this skill's job is to make the reviewer see the boundary the framework
obscured.
🎯 Why: Design for Change
The goal of writing software is to be able to change it safely. Secure-by-default config (CSP, cookie flags, parameterized queries, authz-at-the-edge) means the next feature ships without re-litigating the threat model. Every insecure default you accept becomes a foothold the next change has to step around.
This skill is for security review and secure implementation. For general
TypeScript correctness use typescript-best-practices; for schema-level
integrity use postgres-dba. This skill never assumes another layer will
catch it.
How to use this skill (review workflow)
- Map the attack surface first. Identify every trust boundary: HTTP
handlers, Server Actions, form posts, websocket frames, file uploads,
outbound fetches,
postMessage,process.envreaching the client, third-party script tags. A vuln you didn't enumerate is a vuln you didn't find. - Triage each input against the decision guide below; open the matching
references/*.mdfor the exploit, the vulnerable pattern, the fix, and the false-positive caveat. - Apply the framework reference (
references/nextjs.md,nuxt.md,bun.md,hono.md) — the generic finding almost always has a framework-specific trap or a framework-specific fix. - Report findings in the standard format (
templates/finding.md): severity, location (file:line), a concrete exploit walkthrough, and the minimal fix. No exploit path stated → it is an observation, not a finding; say which. - Recommend the secure default, not a bespoke patch. The
templates/configs (CSP, security headers, cookies, CORS) are the target state; a one-off escape is a stopgap.
What ships with it
12 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.
- .DS_Store 6.0 KB
- references/backend.md 13 KB
- references/bun.md 4.1 KB
- references/frontend.md 8.9 KB
- references/hono.md 4.4 KB
- references/nextjs.md 4.2 KB
- references/nuxt.md 3.6 KB
- templates/cors.md 1.8 KB
- templates/finding.md 1.9 KB
- templates/input-validation.ts 2.1 KB runs code
- templates/review-checklist.md 2.4 KB
- templates/security-headers.md 3.4 KB
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.
- 2mo ago First seen · 208 lines · 207 tokens per session scan A e9026350da7e
security-web is a skill published in the GitHub repository robconery/cassini-workshop (1 stars, last pushed 4mo ago), licensed MIT. It adds 207 tokens to every session and 3,019 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to security-web, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
frontmcp-setup
Use when starting, scaffolding, or organizing a FrontMCP project. Covers creating a new project (CLI scaffold or manual) for Node, Vercel, and other targets; standalone versus Nx-monorepo layout, naming conventions, generators, and dependency rules; composing multiple @App classes, ESM packages, and remote MCP servers…
edge-commerce
Reduce latency globally by running geo-routing, A/B tests, and personalization logic at the network edge using Cloudflare Workers or Vercel.
review-stack
Stack review of one or more third-party tools (OXC, TanStack, Vite, cf, Sentry, pnpm, Claude Code...) against current official best practices, or of what a dependency bump brings (bumped): one parallel subagent per tool, verified findings, one consolidated plan in chat. USE WHEN: user runs /review-stack or explicitly…
spatialite
Use when adding spatial SQL to a single-file SQLite database with SpatiaLite — modspatialite loading, InitSpatialMetaData, AddGeometryColumn, CreateSpatialIndex/MbrWithin, STTransform and GEOS predicates, spatialitetool or ogr2ogr import of Shapefile, and GPKG fallback; also for 'no such module: modspatialite', 'no…
research-brief
Produce a concise source-backed research brief with tradeoffs and confidence.
cf
USE WHEN: running, finding, or troubleshooting Cloudflare CLI (cf) commands in this repo - dev servers, builds and their Build Output, Env types, startup profiling, production profiles, Workers Issues, and telemetry, local KV/D1/R2 data, the commands that still need Wrangler, or the cf equivalent of a Wrangler habit.…