New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Audit Browser Security Boundaries

by nordstjernen-web in nordstjernen-web/northstar-browser

Audit browser-engine changes that process untrusted content or cross native-memory, origin, network, storage, extension, decoder, sandbox, or operating-system boundaries.

GPL-3.0Auto-check passedSecurity

Install Audit Browser Security Boundaries

skills CLI
$ npx skills add nordstjernen-web/northstar-browser --skill audit-browser-security-boundaries -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nordstjernen-web/northstar-browser audit-browser-security-boundaries --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/nordstjernen-web/northstar-browser.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/audit-browser-security-boundaries .claude/skills/audit-browser-security-boundaries && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
audit-browser-security-boundaries
GitHub stars
128
Token cost
~920 tokens
SKILL.md length
449 words
Files
2
Skills in repo
5
Repo updated
First seen
Licence
GPL-3.0

At a glance

Audit browser-engine changes that process untrusted content or cross native-memory, origin, network, storage, extension, decoder, sandbox, or operating-system boundaries.

  • Works in 3 steps: Identify the attacker-controlled entry… → Trace changed values through parsers,… → Distinguish prevention boundaries such…
  • Security reviews
  • SKILL.md covers Model the path, Review the invariants, Report or fix and Substantiate the finding, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Audit Browser Security Boundaries is an agent skill from nordstjernen-web/northstar-browser. Audit browser-engine changes that process untrusted content or cross native-memory, origin, network, storage, extension, decoder, sandbox, or operating-system boundaries. Use for security reviews, threat analysis, and security fixes where parsing, lifetime, isolation, or containment guarantees could regress.

Its SKILL.md is about 920 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Security, covering Threat modeling and Security review. The repository describes itself as: Northstar web browser, Open Source License: GPL v3. Northstar web browser is a real web browser, not based on Firefox or Chrome. The licence is GPL-3.0.

When your agent uses it

  • Security reviews
  • Threat analysis
  • Security fixes where parsing
  • Containment guarantees could regress

Example prompts

  • “/audit-browser-security-boundaries”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Identify the attacker-controlled entry point, trust transition, security invariant, sensitive operation, and possible impact.
  2. Trace changed values through parsers, conversions, queues, callbacks, caches, persistence, and native APIs to their final use.
  3. Distinguish prevention boundaries such as origin checks from containment boundaries such as a process sandbox. Do not claim one provides…

What it can do on your machine

Read from SKILL.md and the folder at commit 5a86d8b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Audit Browser Security Boundaries loads about 920 tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 449 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~920

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from nordstjernen-web/northstar-browser at commit 5a86d8b, republished under its GPL-3.0 licence (© nordstjernen-web). 449 words, ~920 tokens.

Download SKILL.mdSave it as .claude/skills/audit-browser-security-boundaries/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
audit-browser-security-boundaries
description
Audit browser-engine changes that process untrusted content or cross native-memory, origin, network, storage, extension, decoder, sandbox, or operating-system boundaries. Use for security reviews, threat analysis, and security fixes where parsing, lifetime, isolation, or containment guarantees could regress.

Audit Browser Security Boundaries

Read the repository instructions, threat model, changed code, and its callers. Preserve unrelated changes. Treat all fetched content and metadata as attacker-controlled unless the threat model says otherwise.

Model the path

  1. Identify the attacker-controlled entry point, trust transition, security invariant, sensitive operation, and possible impact.
  2. Trace changed values through parsers, conversions, queues, callbacks, caches, persistence, and native APIs to their final use.
  3. Distinguish prevention boundaries such as origin checks from containment boundaries such as a process sandbox. Do not claim one provides the other.

Review the invariants

  • Memory: length conversion, arithmetic overflow, allocation caps, bounds, nesting depth, cleanup, ownership, and use-after-free
  • Lifetime and concurrency: cancellation, callbacks, worker threads, shared state, teardown order, and stale native handles
  • Web security: URL canonicalization, same-origin checks, site partitioning, redirects, mixed content, CORS, CSP, SRI, scopes, and permissions
  • Persistence: private mode, path containment, file permissions, cache keys, secret handling, and extension identity
  • Containment: privilege drop, syscall and filesystem restrictions, executable-memory policy, child processes, and platform-specific mitigations

Do not weaken verification, limits, isolation, or sandbox rules to improve compatibility. Prefer fail-closed behavior at security boundaries.

Report or fix

For a review, report only findings with a concrete attacker path and consequence. Include severity, exact evidence, violated invariant, impact, and the smallest safe correction. Do not edit code during a review-only request.

For a requested fix, reuse established security helpers and keep equivalent platform paths aligned where capabilities overlap. Compile and exercise the affected path, run deterministic smoke cases, and update the threat-model documentation only when its guarantees change.

Show full SKILL.md (190 more words)Show less

Substantiate the finding

Reading a code path is enough to raise a suspicion, not to report it. Reach the behavior through the real browser: a minimal local page for parser and DOM paths, the headless driver with --debug=net,error for fetch, cache, and policy paths. Report what the browser did, and say plainly when a finding is reasoned rather than observed.

The same evidence protects a fix. A security correction that cannot be shown to change the observed behavior has not been verified, and one that changes behavior on paths the report never mentioned needs its blast radius established before it lands.

Northstar context

Read SECURITY.md. Northstar processes untrusted pages in a single native process, so JavaScript realm separation does not contain native memory corruption. Pay particular attention to src/security.c, src/net.c, src/csp.c, src/cache.c, src/idb.c, src/ext.c, src/js.c, image/audio decoders, and platform startup code.

The repository's helper scripts export NS_ALLOW_ROOT so headless runs bypass the privileged-startup refusal. That is a convenience for local fixtures, not a statement about the product: never carry it into a claim that the refusal is optional, and never widen it in the engine to make a scenario reproduce.

© nordstjernen-web, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/audit-browser-security-boundaries of nordstjernen-web/northstar-browser.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 5a86d8b

Compare with similar skills

Audit Browser Security Boundaries next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Audit Browser Security Boundaries compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Audit Browser Security Boundaries this skillnordstjernen-web/northstar-browser128—~920Automated safety check: PassGPL-3.0
Commit Security Scancodexstar69/bug-hunter520—~629Automated safety check: PassMIT
Auditing Code For Vulnerabilitiestrilwu/secskills157—~3.2kAutomated safety check: PassMIT
Threat Mitigation Mappingwshobson/agents40k8 repos~742Automated safety check: PassMIT
Security Auditblueberrycongee/termcanvas405—~966Automated safety check: NotesMIT
Security Reviewcodexstar69/bug-hunter520—~567Automated safety check: PassMIT

Similar skills

  • Commit Security Scan

    codexstar69/bug-hunter

    Scan code changes for security vulnerabilities using Bug Hunter-native artifacts and STRIDE context.

    520 GitHub stars~629 tokensUpdated 1 mo ago
    SecurityAuto-check passed

  • Auditing Code For Vulnerabilities

    trilwu/secskills

    Audit source code for exploitable vulnerabilities using threat-model-driven review, taint tracing, invariant checking, and variant analysis.

    157 GitHub stars~3.2k tokensUpdated 1 mo ago
    SecurityAuto-check passed

  • Threat Mitigation Mapping

    wshobson/agents

    Match identified threats to preventive, detective and corrective controls across network, application, data, endpoint and process layers to plan remediation.

    40k GitHub starsUsed in 8 repos~742 tokens
    SecurityAuto-check passed

  • Security Audit

    blueberrycongee/termcanvas

    Security audit skill. An agent skill from blueberrycongee/termcanvas.

    405 GitHub stars~966 tokensUpdated 4 mo ago
    SecurityAuto-check: notes

  • Security Review

    codexstar69/bug-hunter

    Run a focused STRIDE-based security review using Bug Hunter-native artifacts.

    520 GitHub stars~567 tokensUpdated 1 mo ago
    SecurityAuto-check passed

  • Commit Security Scan

    Factory-AI/factory-plugins

    Analyze code changes for security vulnerabilities using LLM reasoning and threat model patterns.

    111 GitHub stars~2.3k tokensUpdated today
    SecurityAuto-check passed

More from nordstjernen-web/northstar-browser

  • Port Engine Changes

    nordstjernen-web/northstar-browser

    Port a browser-engine change between sibling editions or long-lived branches of the same codebase, in either direction.

    128 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Build Northstar

    nordstjernen-web/northstar-browser

    Configure, compile, and smoke-test a Meson-based C or C++ desktop browser on Linux, macOS, or Windows, and diagnose dependency, compiler, linker, runtime-library, build-directory, or…

    128 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

  • Diagnose Rendering Regressions

    nordstjernen-web/northstar-browser

    Diagnose and fix visual, geometry, hit-testing, and viewport regressions in a browser rendering engine.

    128 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Fix Web Platform Compat

    nordstjernen-web/northstar-browser

    Diagnose and fix standards-compatibility gaps in a browser engine across HTML, DOM, JavaScript bindings, events, CSSOM, forms, fetch, storage, and Web APIs.

    128 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

Categories

Questions about Audit Browser Security Boundaries

What does Audit Browser Security Boundaries do?

Audit browser-engine changes that process untrusted content or cross native-memory, origin, network, storage, extension, decoder, sandbox, or operating-system boundaries. Audit Browser Security Boundaries is an agent skill from nordstjernen-web/northstar-browser. Audit browser-engine changes that process untrusted content or cross native-memory, origin, network, storage, extension, decoder, sandbox, or operating-system boundaries.

When should I use Audit Browser Security Boundaries?

Audit Browser Security Boundaries fits situations like: security reviews; threat analysis; security fixes where parsing; containment guarantees could regress.

How do I install Audit Browser Security Boundaries in Claude Code?

Run `npx skills add nordstjernen-web/northstar-browser --skill audit-browser-security-boundaries -a claude-code`. Or copy the skill folder (.agents/skills/audit-browser-security-boundaries in nordstjernen-web/northstar-browser) into .claude/skills/audit-browser-security-boundaries in your project. Claude Code loads it when a task matches its description.

How do I install Audit Browser Security Boundaries in Codex?

Run `npx skills add nordstjernen-web/northstar-browser --skill audit-browser-security-boundaries -a codex`. Or copy the skill folder (.agents/skills/audit-browser-security-boundaries in nordstjernen-web/northstar-browser) into .agents/skills/audit-browser-security-boundaries in your project. Codex loads it when a task matches its description.

Can I use Audit Browser Security Boundaries in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nordstjernen-web/northstar-browser --skill audit-browser-security-boundaries -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audit-browser-security-boundaries, .gemini/skills/audit-browser-security-boundaries, .github/skills/audit-browser-security-boundaries and .opencode/skills/audit-browser-security-boundaries in your project.

What does Audit Browser Security Boundaries need to run?

SKILL.md names no scripts, command-line tools or credentials: Audit Browser Security Boundaries is instructions for the agent only.

Does Audit Browser Security Boundaries access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Audit Browser Security Boundaries safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Audit Browser Security Boundaries use?

Audit Browser Security Boundaries is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Audit Browser Security Boundaries use?

About 920 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Audit Browser Security Boundaries?

Skills that share tags, products or a category with Audit Browser Security Boundaries: Commit Security Scan (codexstar69/bug-hunter, 520 stars), Auditing Code For Vulnerabilities (trilwu/secskills, 157 stars), Threat Mitigation Mapping (wshobson/agents, 40k stars) and Security Audit (blueberrycongee/termcanvas, 405 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Audit Browser Security Boundaries?

nordstjernen-web (a GitHub organization) maintains it in nordstjernen-web/northstar-browser, which has 128 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 10, 2026.

Source: nordstjernen-web/northstar-browser on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.