Shell Tool · engineering · Sentinel

Security Review

OWASP Top 10 walk against the codebase with concrete proof-of-concept exploits per finding.

Updated today

View as MarkdownsentinelsonnetstandardMax 12 turns

Overview

Walks OWASP Top 10 against the codebase in /work via shell_read + grep + targeted endpoint probes. For every finding, builds a CONCRETE proof-of-concept (the curl command, the payload, the exact line in the code) — vague 'might be vulnerable to XSS' is forbidden. Proposes the minimum patch per finding (minimal-patch discipline).

When to use this

user wants a security review of their code
user says 'security audit' / 'check this for vulnerabilities' / 'OWASP review'
user is shipping to production and wants a pre-launch security check

When NOT to use this

user wants a LIVE site audited (not source) → use website-audit with focus=security
user wants to fix one specific vuln → use minimal-patch directly

Example prompts

security review of /work — OWASP Top 10

audit my API for SQL injection

check this auth flow for vulnerabilities

Inputs and output

Inputs

Field	Description
`scope`	path or glob to audit (default /work)

Output

Per-finding report: file:line, severity, PoC, proposed minimal patch.

Runtime profile

What the engine commits when this skill runs.

Property	Value	Meaning
Model tier	`sonnet`	The balanced default model class. Trades quality against cost for the vast majority of skill runs.
Cost class	`standard`	The balanced default model. Right for most skills.
Turn budget	`12`	Hard cap on tool-calling iterations before the engine forces a final answer.
Execution	`synchronous`	Runs inside the live turn; result lands in the same response.

Under the hood

Tools the engine exposes to this skill and integrations it needs.

Resource	Kind
`shell_exec`	tool
`shell_read`	tool

Tags: engineering, security, audit

Execution template

Shell tools dispatch via a command template. The model substitutes user inputs into the placeholders before firing the underlying tool.

shell_execbash

1OWASP-10 walk against {{scope}}; build PoC per finding; propose minimum patch per minimal-patch/SKILL.md

Related skills

Skill	What it does
Spin up a Web App	Scaffold a fresh web app in /work, start the dev server, surface the live preview URL.
Clone a Website	Fire ultron-capture: spider the site, deploy a branded clone, surface the URL when ready.
Build an Agent	Spin up an autonomous agent on the agent-runtime satellite — try templates first, custom build only if no fit.
Deploy to Cloudflare	Ship the current /work to Pages, Workers, or Containers — then verify the live URL.
Push to GitHub	Initialize /work as a git repo, create the GitHub repo, push, return the URL.
Swap Page Sections	Reorder <section> blocks in a minified HTML file with byte-level safety.

Invoking this from an agent

Three paths reach this skill. From the chat UI, a user can type the persona slash command followed by a natural request and the discovery step resolves to this skill automatically. From the MCP server, fetch the skill detail with get_skill({id: "security-review"}) and then invoke it through the agent runtime once the authenticated tier ships. From your own code, hit /docs/skills/security-review/llm.txt for the token-efficient markdown body and feed it to your model directly.

Note

Every skill page has a canonical permalink and a markdown alternate that LLM crawlers consume via Accept: text/markdown. The full machine-readable catalog lives at /.well-known/agent-skills/index.json.