web-app-penetration-testing

A skill for authorized, end-to-end security testing of a running web application or website. It uses Strix agents to try real attacks, such as authentication bypasses, access-control failures, injection, cross-site scripting, and server-side request forgery, then proves each finding.

In plain words
What is it for?
Use it against a permitted production, staging, or local web app when you want black-box penetration testing with validated exploit demonstrations.
Why use it?
It helps reveal vulnerabilities in the live application's behavior instead of checking source code or relying only on security signatures.

Skill for Claude CodeCodex

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 skills/usestrix/strix/web-app-penetration-testing
Any agent
npx skills add usestrix/strix --skill web-app-penetration-testing
Clone the repo
git clone --depth 1 https://github.com/usestrix/strix

Made for: Claude Code, Codex.

Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 958 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00129 $0.00958
Opus 5 $0.00064 $0.00479
Sonnet 5 $0.00026 $0.00192
Haiku 4.5 $0.00013 $0.00096

Measured yesterday against content hash 7b345118ed8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-app-penetration-testing 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 yesterday.

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.

skills/web-app-penetration-testing/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pentest a web application

Black-box (and optionally source-assisted) penetration testing of a running web app with Strix's autonomous agents. Every reported finding is validated with a working exploit, so there are no signature-based false positives to triage.

Install, LLM setup, all CLI flags, and the managed-cloud alternative are covered in the penetration-testing-with-strix skill — read it if the target is not a running web app, or if strix --version fails. This skill is the web-app-specific workflow.

1. Confirm authorization and scope

Before running anything, establish:

  • The target is the user's (or they are explicitly authorized to test it). Never pentest a third-party site on a hunch.
  • Which environment. Prefer staging over production; agents send real exploit payloads and will create/modify data.
  • Out-of-scope paths — payment flows, mass-email endpoints, admin destructive actions, third-party SSO providers.
  • Credentials. Most real vulnerabilities live behind login. Without a test account, the agents only ever see the marketing surface.

Ask for anything missing rather than guessing.

2. Run the scan

strix -n -t https://staging.example.com --max-budget 20 \
  --instruction "Test account: [email protected] / <password>. In scope: /app/*, /api/*. Do not touch /billing or send email. Focus on access control between the two seeded orgs."

Notes that matter for web apps specifically:

  • Give it credentials via --instruction (or --instruction-file for anything long), including how to log in if the flow is unusual (magic link, SSO, MFA-exempt test user).
  • Two accounts beat one. Multi-tenant IDOR and broken-access-control bugs — consistently the highest-impact class in web apps — can only be proven when the agent can attempt cross-account access.
  • Add the repo for white-box depth when you have the source: -t https://github.com/org/app -t https://staging.example.com (or a local path). Source access materially improves coverage of business-logic and authorization flaws.
  • Localhost works. Point at http://host.docker.internal:3000 (Docker Desktop) so the sandbox can reach a dev server on the host.
  • --scan-mode quick for a fast dev-loop pass, standard (~30 min) for a normal review, deep for pre-release assurance. Always set --max-budget.

Read the full file on GitHub · 55 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. yesterday First seen · 55 lines · 129 tokens per session scan A 7b345118ed8e

Subscribe to this mod's changes

web-app-penetration-testing is a skill published in the GitHub repository usestrix/strix (59,426 stars, last pushed 3d ago), licensed Apache-2.0. It adds 129 tokens to every session and 958 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.