Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

Claude-Code-Quest

skill · wesammustafa/Claude-Code-QuestNOASSERTION licenceAudited 12 Nov 2026 · source b10a6f22c870

★ 3,687pushed 1 day ago
!CAUTIONGrade D · 69/100 · 25 findings · b10a6f2
3,687repo stars · whole wesammustafa/Claude-Code-Quest

Is it safe? With care — CAUTION, grade D (69/100). We read this skill's source at commit b10a6f22c870 and observed filesystem and network access and no hard-coded secrets. The audit raised 25 findings, 0 critical or high. What it does: The team's review of a change to linkcheck, run the same way on a laptop and in CI. Use on a staged diff or a pull request.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Claude-Code-Quest (wesammustafa/Claude-Code-Quest)”. Retrieved 12 Nov 2026. https://modelsatlas.com/skills/wesammustafa/claude-code-quest

Trust audit

Audit 0.4.1 · source read 12 Nov 2026

Trust score69/100!CAUTION D
0 critical0 high4 medium38 low0 info

CAUTION means the audit found things worth knowing before you trust this skill. Grade D is shared by 749 of 18,389 audited skills.

What the source does

  • FilesystemDeclared2 observations
  • NetworkDeclared1 observation
  • ShellNone observedNo commands run in the source
  • DependenciesNot pinnedSome versions float
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityWARN2
L1 Static sourceSecrets, path traversal, supply chain, hidden codeWARN20
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS3
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (25)

MEDIUMInventory / provenanceinv.binary · quest/client/pip/pip.riv
F-13 Inventory / provenanceCWE-1104Layer L0
pip.riv
Why
a compiled or binary member cannot be reviewed from source
Fix
ship source, or explain the binary in the README
MEDIUMNetwork egressnet.raw_ip · quest/client/playwright.config.ts:3
F-04 Network egressCWE-200 · CWE-319Layer L1
const PREVIEW = "http://127.0.0.1:4319";
Why
No further detail recorded for this rule.
Fix
—
MEDIUMObfuscation / stealthobf.zero_width · practice-template/checks/frontmatter.mjs:44
F-07 Obfuscation / stealthCWE-506 · CWE-94Layer L1
const lines = (text ?? '').replace(/^/, '').split(/\r?\n/);
Why
No further detail recorded for this rule.
Fix
—
MEDIUMObfuscation / stealthobf.zero_width · practice-template/checks/lessons/b-5.mjs:84
F-07 Obfuscation / stealthCWE-506 · CWE-94Layer L1
const firstLine = (/** @type {Repo} */ repo, /** @type {string} */ sha, /** @type {string} */ path) => /** @type {string} */ (repo.git('show', `${sha}:./${path}`).replace(/^/, '').split(/\r?\n/)[0]).t
Why
No further detail recorded for this rule.
Fix
—
LOWInventory / provenanceinv.hidden_file · .prettierignore
F-13 Inventory / provenanceCWE-1104Layer L0
.prettierignore
Why
hidden member outside the usual dotfiles
Fix
review its purpose
LOWInsecure cryptocrypto.weak_hash · quest/engine/src/holds.ts:153
F-09 Insecure cryptoCWE-327 · CWE-338Layer L1
createHash("sha1").update(buf).digest("hex").slice(0, 12);
Why
No further detail recorded for this rule.
Fix
—
LOWInsecure cryptocrypto.weak_hash · quest/engine/src/status.ts:78
F-09 Insecure cryptoCWE-327 · CWE-338Layer L1
createHash("sha1")
Why
No further detail recorded for this rule.
Fix
—
LOWInsecure cryptocrypto.weak_hash · quest/host/src/probes.ts:34
F-09 Insecure cryptoCWE-327 · CWE-338Layer L1
createHash("sha1").update(text).digest("hex").slice(0, 16);
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · .github/scripts/fixtures/broken-link-in-live-config/generate.mjs:9
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
'---\ndescription: Review a page\n---\n\nFollow [the style guide](../../../STYLE.md).\n',
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · .github/scripts/test/no-platform-skips.test.mjs:9
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
const root = fileURLToPath(new URL("../../../", import.meta.url));
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · .github/scripts/test/retired-rules.test.mjs:8
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
const root = new URL("../../../", import.meta.url);
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · .github/scripts/test/security-doc.test.mjs:8
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
const root = new URL("../../../", import.meta.url);
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · practice-template/checks/test/advanced.test.mjs:2349
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
[{ name: 'team-kit', source: './plugins/../../team-kit' }, /whose `\.\.` leaves the marketplace folder/],
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.raw_ip · .github/scripts/fixtures/broken-external-link/tree/README.md:3
F-04 Network egressCWE-200 · CWE-319Layer L1
See [the vendor docs](http://127.0.0.1:9/setup).
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.raw_ip · docs/intermediate/electives/claude-in-chrome.md:46
F-04 Network egressCWE-200 · CWE-319Layer L1
Open http://127.0.0.1:8000/ui-demo.html and tell me what the page shows. Read its console for errors, reloading the page if you need to catch errors from page load, and save a screenshot of it to disk
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.raw_ip · practice-template/checks/test/advanced.test.mjs:1472
F-04 Network egressCWE-200 · CWE-319Layer L1
const fake = { ANTHROPIC_API_KEY: 'not-a-key', ANTHROPIC_AUTH_TOKEN: 'not-a-token', CLAUDE_CODE_OAUTH_TOKEN: 'not-a-token', ANTHROPIC_BASE_URL: 'http://127.0.0.1:9' };
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.raw_ip · quest/client/e2e/pip.spec.ts:144
F-04 Network egressCWE-200 · CWE-319Layer L1
expect(wasm?.origin).toBe("http://127.0.0.1:4319");
Why
No further detail recorded for this rule.
Fix
—
LOWObfuscation / stealthobf.zero_width · practice-template/checks/test/advanced.test.mjs:1433
F-07 Obfuscation / stealthCWE-506 · CWE-94Layer L1
for (const result of [{ ...REAL_RUN, num_turns: 6 }, utf16(JSON.stringify(REAL_RUN, null, 2)), `${JSON.stringify(REAL_RUN)}`]) {
Why
No further detail recorded for this rule.
Fix
—
LOWObfuscation / stealthobf.zero_width · practice-template/checks/test/advanced.test.mjs:2023
F-07 Obfuscation / stealthCWE-506 · CWE-94Layer L1
{ runs: (sha) => `${JSON.stringify([runOf(sha)])}` },
Why
No further detail recorded for this rule.
Fix
—
LOWObfuscation / stealthobf.zero_width · practice-template/checks/test/advanced.test.mjs:3130
F-07 Obfuscation / stealthCWE-506 · CWE-94Layer L1
for (const slice of [`${JSON.stringify(SLICE_RUN)}`, utf16(JSON.stringify(SLICE_RUN, null, 2)), `${stream}\n`, { ...SLICE_RUN, total_cost_usd: 1.99 }]) {
Why
No further detail recorded for this rule.
Fix
—
LOWSupply chainsupply.unpinned · quest/release/test/fixtures/project/app/package.json
F-08 Supply chainCWE-829 · CWE-1357Layer L1
shared
Why
1 dependency range(s) float
Fix
pin exact versions or ship a lockfile
LOWSupply chainsupply.unpinned · quest/release/test/fixtures/project/packages/ok-lib/package.json
F-08 Supply chainCWE-829 · CWE-1357Layer L1
inner
Why
1 dependency range(s) float
Fix
pin exact versions or ship a lockfile
LOWPrompt injectionprompt.authority_framing · docs/advanced/07-bounded-runs.md:133
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
- Your bounds don't cover everything the run loads. Hooks and local MCP servers run outside the sandbox with your full access ([What runs outside the sandbox](https://code.claude.com/docs/en/sandboxin
Why
No further detail recorded for this rule.
Fix
—
LOWPrompt injectionprompt.authority_framing · docs/intermediate/04-permissions-and-sandbox.md:107
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
- The sandbox wraps shell commands only. Claude's file and web tools follow permission rules; hooks and local MCP servers run outside it with your full access ([What runs outside the sandbox](https://
Why
No further detail recorded for this rule.
Fix
—
LOWPrompt injectionprompt.credential_read · .github/scripts/fixtures/lesson-watch-out-too-long/tree/docs/intermediate/05-hooks.md:70
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
"deny": ["Read(.env)"]
Why
asks the agent to read credentials
Fix
—

Audit 0.4.1 · source sha b10a6f22c870 · 12 Nov 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherwesammustafa GitHub userOwner of the repository this skill is read from
  • Source folderwesammustafa/Claude-Code-QuestThe exact folder we audited
  • LicenceNOASSERTIONAs the repository states it
  • Commit pinned for this verdictb10a6f22c870A new audit runs when the source changes
  • Repository statusNot archivedLast push 1 day ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: The team's review of a change to linkcheck, run the same way on a laptop and in CI. Use on a staged diff or a pull request.

---
name: team-review
description: The team's review of a change to linkcheck, run the same way on a laptop and in CI. Use on a staged diff or a pull request.
---

Review the change you are given (a staged diff on stdin, or the pull request's diff) and change no file.

Report each finding as `file:line` and why, in this order:

1. A bug: a link that would be reported wrongly, or a crash on some input.
2. A changed function in `src/` without a test in `test/` that fails without the change.
3. An error message that doesn't start with `linkcheck:` or doesn't say what to do next.

If you find nothing, say so in one line.

Excerpt, first 624 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit b10a6f2

Download folder ↗
git clone --bare <template copy> av-origin.git
git clone av-origin.git av-practice
claude plugin install commit-helper@<you>-plugins
claude mcp add --env CHROME_DEVTOOLS_MCP_NO_UPDATE_CHECKS=1 --transport stdio chrome-devtools -- npx -y [email protected] --i
claude mcp add --scope project --env CHROME_DEVTOOLS_MCP_NO_UPDATE_CHECKS=1 --transport stdio chrome-devtools -- npx -y chrome-devtool
npm install -g typescript-language-server typescript@6

Commands as the repository documents them: shown, never run by us. Our verdict covers commit b10a6f22c870 only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
Claude DesktopMentioned in its text, not testedSkills for Claude Desktop · About Claude Desktop
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. !CAUTION D 69 / 100

    first audit · source b10a6f22c870

README badge

For maintainers · shows the latest audit

ModelsAtlas: CAUTION DMODELSATLASCAUTION · D
[![ModelsAtlas: CAUTION D](https://modelsatlas.com/skills/wesammustafa/claude-code-quest/badge.svg)](https://modelsatlas.com/skills/wesammustafa/claude-code-quest/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Claude-Code-Everything-You-Need-to-Know✓SAFE

wesammustafa/Claude-Code-Everything-You-Need-to-Know

Audit a CLAUDE.md file for the patterns that actually degrade Claude Code's output — vagueness, unnamed files, stale facts, and bloat. Use when asked to review, audit, improve, shrink, or fix a CLAUDE.md, and when a…

★ 3.2kGrade B
agent-browser✓SAFE

shanraisshan/claude-code-best-practice

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating…

★ 68kGrade B
Weather Fetcher!CAUTION

shanraisshan/claude-code-best-practice

Instructions for fetching current weather temperature data for Dubai, UAE from Open-Meteo API

★ 68kGrade B
Weather Transformer✓SAFE

shanraisshan/claude-code-best-practice

from vibe coding to agentic engineering - practice makes claude perfect

★ 68kGrade B
awesome-claude-code✓SAFE

hesreallyhim/awesome-claude-code

A hand-picked collection of the finest of resources for the most awesome of agents, Claude Code, the undisputed champion of coding companions, from the unstoppable team at Anthropic PBC. A delectable showcase of top…

★ 55kGrade B
Research!CAUTION

alirezarezvani/claude-skills

Default entry point for any research request — a hybrid router that classifies the question deterministically and either delegates to a specialist research skill (pulse for trends/sentiment, grants for NIH funding,…

★ 28kGrade B

Add this badge to your README

[![ModelsAtlas: CAUTION D](https://modelsatlas.com/skills/wesammustafa/claude-code-quest/badge.svg)](https://modelsatlas.com/skills/wesammustafa/claude-code-quest/)

Questions about Claude-Code-Quest

What does the Claude-Code-Quest skill do?
Claude Code guide in three levels, Beginner to Advanced: hands-on lessons with checked exercises, every volatile fact cited to its source. Independent community guide.
Is Claude-Code-Quest safe to install?
With care. The audit graded it D (69/100) and found 25 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can Claude-Code-Quest access on my machine?
The audit observed that it reaches the network and reads or writes files. Each of those is consistent with what it says it does. Secrets in the source: none found.
Which assistants does Claude-Code-Quest work with?
Its documentation mentions claude-code and claude-desktop. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (b10a6f22c870), read on 2026-11-12. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.