Agent skill · Audited from source

claude-codex-settings

skill · fcakyon/claude-codex-settingsApache-2.0 licenceAudited 20 Oct 2026 · source 256a8f0dd4a8

★ 1,181pushed todayversion 0.1.2

✕BLOCKGrade F · 35/100 · 25 findings · 256a8f0

1,181repo stars · whole fcakyon/claude-codex-settings

Read the findings View source on GitHub ↗

Is it safe? No — BLOCK, grade F (35/100). We read this skill's source at commit 256a8f0dd4a8 and observed filesystem, network and shell access and a hard-coded secret (see the findings). The audit raised 25 findings, 9 critical or high. What it does: This skill should be used when the user asks for "ADHD output", "fewer output tokens", "short numbered steps", "limited working memory formatting", or explicitly invokes "adhd-output-style".

Ask an AI about this pageGChatGPT CClaude PPerplexity GeGemini XGrok

CoCopilot AIGoogle AI Mode

Cite

Cite this page

ModelsAtlas. “claude-codex-settings (fcakyon/claude-codex-settings)”. Retrieved 20 Oct 2026. https://modelsatlas.com/skills/fcakyon/claude-codex-settings

Blocked. The page stays public so you can check this skill if someone recommended it to you. The audit found 9 critical or high findings, starting with “Prompt injection” in plugins/agent-browser/skills/agent-browser/SKILL.md:260. Do not install it without reading them.

Trust audit

Audit 0.4.1 · source read 20 Oct 2026

Trust score35/100✕BLOCK F

2 critical7 high10 medium29 low0 info

BLOCK means the audit found something that could harm you or your machine. Grade F is shared by 105 of 14,816 audited skills.

What the source does

FilesystemDeclared2 observations
NetworkDeclared4 observations
ShellDeclared5 observations
DependenciesNot pinnedSome versions float
SecretsFoundSee the findings; values are never shown

Five audit layers

Layer	What we check	Result	Findings
`L0` Provenance	Repo owner, licence, archive status, activity	PASS	3
`L1` Static source	Secrets, path traversal, supply chain, hidden code	FAIL	14
`L2` Instructions	Prompt injection, authority framing, hidden directives	FAIL	8
`L3` Inventory	The files and declarations match the source	PASS	0
`L4` Sandbox	Run in isolation and watch behaviour	SKIPPED why	0

Gates applied: critical finding, instruction override, no behavioural pass, undeclared transfer.

Findings (25)

CRITICALPrompt injectionprompt.transfer_instruction · plugins/agent-browser/skills/agent-browser/SKILL.md:260

F-01 Prompt injectionCWE-94 · CWE-1427Layer L2

agent-browser auth login my-app --credential-provider vault --item "My App" --url https://app.example.com/login --username-selector "#email" --password-selector "#password"

Why: an instruction to move sensitive data to an outside destination
Fix: remove; a skill never needs the user's secrets off the machine

CRITICALPrompt injectionprompt.transfer_instruction · plugins/agent-browser/skills/agent-browser/SKILL.md:561

F-01 Prompt injectionCWE-94 · CWE-1427Layer L2

Use comma-separated origins only when each is a trusted dashboard URL. Every origin must be a valid exact HTTPS origin, and custom ports must be integers from 1 to 65535. Invalid dashboard options fai

Why: an instruction to move sensitive data to an outside destination
Fix: remove; a skill never needs the user's secrets off the machine

HIGHHard-coded secretssecret.db_uri · plugins/supabase-skills/skills/supabase-cli/references/examples.yaml:84

F-03 Hard-coded secretsCWE-798 · CWE-321Layer L1

DB URL: postgresql://…@127.0.0.1:54322/postgres

Why: No further detail recorded for this rule.
Fix: —

HIGHHard-coded secretssecret.db_uri · plugins/supabase-skills/skills/supabase-cli/references/examples.yaml:96

F-03 Hard-coded secretsCWE-798 · CWE-321Layer L1

DB_URL="…"

Why: No further detail recorded for this rule.
Fix: —

HIGHHard-coded secretssecret.db_uri · plugins/supabase-skills/skills/supabase-cli/references/examples.yaml:108

F-03 Hard-coded secretsCWE-798 · CWE-321Layer L1

DB_URL="…"

Why: No further detail recorded for this rule.
Fix: —

HIGHPrompt injectionprompt.fetch_and_trust · plugins/cloudflare-skills/skills/cloudflare-deploy/SKILL.md:13

F-01 Prompt injectionCWE-94 · CWE-1427Layer L2

If the project has a `cloudflare.config.ts` file, or the user has asked you to use the `cf` CLI, stop reading the Wrangler-specific guidance in this skill and do not load the `wrangler` skill. Read th

Why: remote text is to be obeyed as instructions
Fix: —

HIGHPrompt injectionprompt.fetch_and_trust · plugins/cloudflare-skills/skills/sandbox-stable/SKILL.md:69

F-01 Prompt injectionCWE-94 · CWE-1427Layer L2

| `exec`, streaming, background processes | [Commands API](https://developers.cloudflare.com/sandbox/sdk/api/commands/index.md) · [Execute commands](https://developers.cloudflare.com/sandbox/sdk/guide

Why: remote text is to be obeyed as instructions
Fix: —

HIGHPrompt injectionprompt.fetch_and_trust · plugins/ultralytics-dev/skills/ultralytics-platform/SKILL.md:15

F-01 Prompt injectionCWE-94 · CWE-1427Layer L2

`GET https://platform.ultralytics.com/openapi.json`. Treat the live OpenAPI document as authoritative

Why: remote text is to be obeyed as instructions
Fix: —

HIGHPrompt injectionprompt.hide_from_user · plugins/mongodb-skills/skills/mongodb-search-and-ai/references/hybrid-search.md:47

F-01 Prompt injectionCWE-94 · CWE-1427Layer L2

**Version requirements**: `$rankFusion` requires MongoDB 8.0+. `$scoreFusion` requires MongoDB 8.3+. Only proceed with this guide if the use case is lexical prefilters, or if the cluster meets the ver

Why: asks the agent to act without the user's knowledge
Fix: —

MEDIUMInformation disclosuredisclose.log_secret · plugins/cloudflare-skills/skills/turnstile-spin/scripts/widget-create.sh:116

F-12 Information disclosureCWE-209 · CWE-532Layer L1

print(json.dumps({"…":"ok","…":sitekey,"…":secret}))

Why: No further detail recorded for this rule.
Fix: —

MEDIUMNetwork egressnet.raw_ip · .codex/config-kimi.toml:13

F-04 Network egressCWE-200 · CWE-319Layer L1

base_url = "http://127.0.0.1:8787/v1"

Why: No further detail recorded for this rule.
Fix: —

MEDIUMNetwork egressnet.raw_ip · plugins/supabase-skills/skills/supabase-cli/SKILL.md:148

F-04 Network egressCWE-200 · CWE-319Layer L1

# Make schema changes in Supabase Studio (http://127.0.0.1:54323)

Why: No further detail recorded for this rule.
Fix: —

MEDIUMNetwork egressnet.raw_ip · plugins/supabase-skills/skills/supabase-cli/references/examples.yaml:82

F-04 Network egressCWE-200 · CWE-319Layer L1

API URL: http://127.0.0.1:54321

Why: No further detail recorded for this rule.
Fix: —

MEDIUMNetwork egressnet.raw_ip · plugins/supabase-skills/skills/supabase-cli/references/examples.yaml:83

F-04 Network egressCWE-200 · CWE-319Layer L1

GraphQL URL: http://127.0.0.1:54321/graphql/v1

Why: No further detail recorded for this rule.
Fix: —

MEDIUMHard-coded secretssecret.db_uri · plugins/dokploy-skills/skills/dokploy-deploy/references/docker-compose/domains.mdx:137

F-03 Hard-coded secretsCWE-798 · CWE-321Layer L1

- DATA…://…@database:5432/mydatabase

Why: No further detail recorded for this rule.
Fix: —

MEDIUMHard-coded secretssecret.db_uri · plugins/dokploy-skills/skills/dokploy-deploy/references/docker-compose/domains.mdx:228

F-03 Hard-coded secretsCWE-798 · CWE-321Layer L1

- DATA…://…@database:5432/mydatabase

Why: No further detail recorded for this rule.
Fix: —

MEDIUMHard-coded secretssecret.generic · plugins/cloudflare-skills/skills/cloudflare-deploy/references/turn/gotchas.md:102

F-03 Hard-coded secretsCWE-798 · CWE-321Layer L1

const secret = '…';

Why: No further detail recorded for this rule.
Fix: —

MEDIUMPrompt injectionprompt.conditional_escalation · plugins/livekit-skills/skills/running-livekit-simulations/SKILL.md:3

F-01 Prompt injectionCWE-94 · CWE-1427Layer L2

description: 'Runs LiveKit agent simulations and acts on the results. Use when the user says "run my simulations", "regression test my agent before deploying", "run the scenarios", "use lk agent simul

Why: No further detail recorded for this rule.
Fix: —

MEDIUMSupply chainprompt.pipe_to_shell · plugins/azure-tools/commands/setup.md:34

F-08 Supply chainCWE-829 · CWE-1357Layer L2

- Linux: curl -sL https://aka.ms/InstallAzureCLIDeb | sudo bash

Why: No further detail recorded for this rule.
Fix: —

LOWInventory / provenanceinv.symlink · .claude/output-styles/adhd-explanatory.md

F-13 Inventory / provenanceCWE-1104Layer L0

.claude/output-styles/adhd-explanatory.md

Why: link not followed
Fix: —

LOWInventory / provenanceinv.symlink · AGENTS.md

F-13 Inventory / provenanceCWE-1104Layer L0

AGENTS.md

Why: link not followed
Fix: —

LOWInventory / provenanceinv.symlink · GEMINI.md

F-13 Inventory / provenanceCWE-1104Layer L0

GEMINI.md

Why: link not followed
Fix: —

LOWInsecure cryptocrypto.weak_hash · plugins/ultralytics-dev/hooks/scripts/markdown_formatting.py:163

F-09 Insecure cryptoCWE-327 · CWE-338Layer L1

hash_val = hashlib.md5(f"{file_path}_{index}".encode(), usedforsecurity=False).hexdigest()[:6]

Why: No further detail recorded for this rule.
Fix: —

LOWFilesystem / pathfs.credential_store · .github/scripts/sync-hetzner-skills.sh:258

F-05 Filesystem / pathCWE-22 · CWE-59Layer L1

hcloud ssh-key create --name deploy-key --public-key-from-file ~/.ssh/id_ed25519.pub

Why: touches a credential store
Fix: —

LOWFilesystem / pathfs.traversal · plugins/codex-advisor/claude-hooks/scripts/forward_transcript.mjs:9

F-05 Filesystem / pathCWE-22 · CWE-59Layer L1

new URL("../../skills/codex-advisor/scripts/ask_codex.mjs", import.meta.url),

Why: No further detail recorded for this rule.
Fix: —

Audit 0.4.1 · source sha 256a8f0dd4a8 · 20 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

Publisherfcakyon GitHub userOwner of the repository this skill is read from
Source folderfcakyon/claude-codex-settingsThe exact folder we audited
LicenceApache-2.0As the repository states it
Commit pinned for this verdict256a8f0dd4a8A new audit runs when the source changes
Repository statusNot archivedPushed today
Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: This skill should be used when the user asks for "ADHD output", "fewer output tokens", "short numbered steps", "limited working memory formatting", or explicitly invokes "adhd-output-style".

---
name: adhd-output-style
description: This skill should be used when the user asks for "ADHD output", "fewer output tokens", "short numbered steps", "limited working memory formatting", or explicitly invokes "adhd-output-style".
---

Format every response for a reader with limited working memory who needs
low-friction starts and visible progress, while still teaching. Apply to all
interactions in the current task.

## Structure (ADHD)

- Open with the actionable step or the answer, not context or setup.
- Break multi-step work into numbered lists, one action per step.
- End with a single next action that takes under two minutes.
- Keep secondary issues separate; do not bundle them into the main answer.
- Restate progress each turn (e.g. "step 3 of 5"); assume prior context is lost.
- Use concrete time estimates ("~2 min", "3 files"), never vague ones.
- State what now works in plain terms instead of burying it in a recap.
- Describe errors factually: cause, then fix. No alarmed language.
- Cap lists at five items; split longer ones into priority tiers.
- Cut preambles, recaps, and closing pleasantries. Start at the answer, stop when done.

Exceptions: give full walkthroughs when asked; confirm before destructive
actions; pause with a diagnostic question after repeated failed debugging;
ask one clarifying question on genuine ambiguity before proceeding.

## Education (Explanatory)

Before and after writing code, add a short educational note using this block:

`★ Insight ─────────────────────────────────────`
[2-3 codebase-specific educational points]
`─────────────────────────────────────────────────`

Put depth here, not in the main answer. Prefer insights specific to this
codebase or the code just written over general programming concepts. Cap at
three points so the block stays scannable. The rest of the response stays terse.

Excerpt, first 1,861 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 256a8f0

npm install -g @openai/codex
claude plugin install simplify@claude-settings
npm install -g @anthropic-ai/gemini-cli
uv tool install ruff
npm install -g [email protected] prettier-plugin-sh
claude plugin install fable-advisor@claude-settings

git clone https://github.com/fcakyon/claude-codex-settings
git -C claude-codex-settings checkout 256a8f0dd4a8

Commands as the repository documents them: shown, never run by us. Our verdict covers commit 256a8f0dd4a8 only.

Works in which agents?

What its own text says, not a test

“Mentioned” means the skill’s text names the agent. We have not run it there.
Agent	Status	More
Claude Code	Mentioned in its text, not tested	Skills for Claude Code · About Claude Code
Claude Desktop	Mentioned in its text, not tested	Skills for Claude Desktop · About Claude Desktop
Codex	Mentioned in its text, not tested	Skills for Codex · About Codex
GitHub Copilot	Mentioned in its text, not tested	Skills for GitHub Copilot · About GitHub Copilot
Cursor	Mentioned in its text, not tested	Skills for Cursor · About Cursor
Gemini CLI	Mentioned in its text, not tested	Skills for Gemini CLI · About Gemini CLI
OpenClaw	Mentioned in its text, not tested	Skills for OpenClaw · About OpenClaw

Audit history

Every audit, every source change

2026-10-20
✕BLOCK F 35 / 100
first audit · source 256a8f0dd4a8

README badge

For maintainers · shows the latest audit

[![ModelsAtlas: BLOCK F](https://modelsatlas.com/skills/fcakyon/claude-codex-settings/badge.svg)](https://modelsatlas.com/skills/fcakyon/claude-codex-settings/)

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

Similar skills

Command Development✓SAFE

fcakyon/claude-codex-settings

Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.

★ 1.2kGrade B

Commands✓SAFE

fcakyon/claude-codex-settings

Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.

★ 1.2kGrade B

Commit Workflow✓SAFE

fcakyon/claude-codex-settings

Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.

★ 1.2kGrade B

Hook Development✓SAFE

fcakyon/claude-codex-settings

Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.

★ 1.2kGrade B

Linear Usage✓SAFE

fcakyon/claude-codex-settings

Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.

★ 1.2kGrade B

Mcp Integration✓SAFE

fcakyon/claude-codex-settings

Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.

★ 1.2kGrade B

Add this badge to your README

[![ModelsAtlas: BLOCK F](https://modelsatlas.com/skills/fcakyon/claude-codex-settings/badge.svg)](https://modelsatlas.com/skills/fcakyon/claude-codex-settings/)

<a href="https://modelsatlas.com/skills/fcakyon/claude-codex-settings/"><img src="https://modelsatlas.com/skills/fcakyon/claude-codex-settings/badge.svg" alt="ModelsAtlas: BLOCK F"></a>

Questions about claude-codex-settings

What does the claude-codex-settings skill do?

Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.

Is claude-codex-settings safe to install?

No — not without reading the findings first. The audit graded it F (35/100) and found 9 critical or high issues in the source. Each one is listed on this page with the file and line it is on.

What can claude-codex-settings access on my machine?

The audit observed that it reaches the network, runs shell commands and reads or writes files. Each of those is consistent with what it says it does. Secrets in the source: found — see the findings.

Which assistants does claude-codex-settings work with?

Its documentation mentions claude-code, claude-desktop, codex, copilot, cursor, gemini-cli and openclaw. 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 (256a8f0dd4a8), read on 2026-10-20. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

github.com/fcakyon/claude-codex-settings — the audited source at commit 256a8f0dd4a8 and every finding aboveObserved · 20 Oct 2026

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.

What does the claude-codex-settings skill do?
GChatGPT CClaude PPerplexity
Is claude-codex-settings safe to install?
GChatGPT CClaude PPerplexity
What can claude-codex-settings access on my machine?
GChatGPT CClaude PPerplexity