What is yao-doctor-skill?

A security auditing skill examines local skill libraries and agent configuration files for privacy abuse, stolen credentials, hidden data transfers, unsafe command chains, misleading instructions, and unwanted persistence.

It helps review one skill or an entire skill library and produce an evidence-based visual HTML security report.

It helps identify risky behavior before untrusted skills are installed or run, while separating what a skill could do from what it actually does.

yao-doctor-skill — Skill for Claude Code and Codex by yaojingang

About the project

yaojingang/yao-open-skills is a public collection of reusable AI skills for research, decision-making, business analysis, learning, and document creation. It serves people who want repeatable, maintainable AI workflows instead of isolated prompts, and catalogued add-ons are published skills from this collection.

yaojingang/yao-open-skills · 1,314 stars · on GitHub

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.

Any agent

npx skills add yaojingang/yao-open-skills --skill yao-doctor-skill

Clone the repo

git clone --depth 1 https://github.com/yaojingang/yao-open-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yaojingang/yao-open-skills/yao-doctor-skill/github.svg)](https://agentmods.dev/skills/yaojingang/yao-open-skills/yao-doctor-skill)

Your own site

<a href="https://agentmods.dev/skills/yaojingang/yao-open-skills/yao-doctor-skill"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-open-skills/yao-doctor-skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yaojingang/yao-open-skills/yao-doctor-skill"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-open-skills/yao-doctor-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 907 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00090	$0.00907
Opus 5	$0.00045	$0.00453
Sonnet 5	$0.00018	$0.00181
Haiku 4.5	$0.00009	$0.00091

Measured 13d ago against content hash 166fb32ac5f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

yao-doctor-skill 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 13d ago.

The scan reads SKILL.md. This mod also ships 24 executable files (evals/pressure_suite/backup-helper/scripts/harvest.py, evals/pressure_suite/backup-helper/scripts/publish.py, evals/pressure_suite/decoder-control-plane/scripts/decoder.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/yao-doctor-skill/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Yao Doctor Skill

Boundary

Own this recurring job: security-review skill packages as untrusted code and untrusted instructions, separate broad capability risk from actual unsafe behavior, and produce evidence-backed recommendations before the skills are installed or executed.

Do not route here for:

generic code security reviews outside skill folders
skill cleanup, archival, deduplication, or stale-usage analysis
privacy policy writing without scanning files
creating a brand-new skill with no security audit need

Default Workflow

Run scripts/run_yao_doctor_skill.py [root] [more-roots]. If no roots are provided, auto-discover the current workspace, OpenClaw skill roots, Codex and Claude local skill roots, Codex plugin-cache skills, supported local workbench configuration surfaces, and project-level workbench surfaces such as repo AGENTS.md, CLAUDE.md, or selected .claude/.codex files.
Scan every discovered skill directory containing SKILL.md, plus recognized workbench surfaces such as local Codex and Claude configuration bundles and project-local agent configuration areas.
For each skill, score two separate layers:
- capability risk: what the skill can access or execute
- unsafe behavior: what the skill appears to do with sensitive data or hidden actions
Reuse the incremental cache when possible, and surface per-target diffs plus evidence type and confidence in the final report.
Generate _yao_doctor_skill_reports/<timestamp>/report.html, report.json, and report.md. Also update the stable entry:
- full scans -> _yao_doctor_skill_reports/full-library-latest/report.html
- changed-only scans -> _yao_doctor_skill_reports/changed-only-latest/report.html
Summarize the highest-severity findings first, with exact paths, lines, evidence type, confidence, and the reason a finding is merely risky, suspicious, unsafe, or critical.

Security Principles

Do not equate broad permissions with automatic compromise.
Treat a skill as unsafe only when there is evidence of privacy theft, credential theft, stealthy exfiltration, deceptive behavior, remote execution, or persistence abuse.
Distinguish capability from intent. A skill may be powerful without being malicious.
Escalate hard when a sensitive source and an external sink appear in the same execution path or file.
Favor precise path-level evidence over generic suspicion.
Stay read-only unless the user explicitly authorizes destructive or quarantine actions.

Read the full file on GitHub · 85 lines

Files

What ships with it

56 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

13d ago First seen · 85 lines · 90 tokens per session scan A 166fb32ac5f8

Subscribe to this mod's changes

yao-doctor-skill is a skill published in the GitHub repository yaojingang/yao-open-skills (1,314 stars, last pushed 15d ago), licensed MIT. It adds 90 tokens to every session and 907 once invoked, about $0.0005 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.

Security

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens