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.
npx agentmods add skills/microsoft/data-formulator/path-safetynpx skills add microsoft/data-formulator --skill path-safetygit clone --depth 1 https://github.com/microsoft/data-formulatorWhat 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 | $0.00050 | $0.01727 |
| Opus 5 | $0.00025 | $0.00864 |
| Sonnet 5 | $0.00010 | $0.00345 |
| Haiku 4.5 | $0.00005 | $0.00173 |
Grade A, and why
path-safety 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 2d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Path Safety — 服务端安全编码规范
来源:
docs/dev-guides/8-path-safety.md(正式开发规范)+design-docs/issues/002-arbitrary-file-read-audit.md(安全审计复核)。 本文档提炼了 6 条必须遵守的编码规范。违反任一条即可能引入路径穿越(LFI)漏洞。
R1. 文件下载:用 ConfinedDir.resolve() + send_file,禁用 send_from_directory
原因:send_from_directory(dir, user_input) 内部会对 user_input 二次解析路径,与前置安全检查形成 TOCTOU 不一致。
# ❌ BAD — 安全检查用 resolved target,发送用原始 filename,两次解析不一致
target = (scratch_dir / filename).resolve()
target.relative_to(scratch_dir.resolve()) # 检查通过
return send_from_directory(str(scratch_dir), filename) # 再次解析
# ✅ GOOD — 检查和发送用同一个 resolved path
scratch_jail = workspace.confined_scratch
target = scratch_jail.resolve(filename)
return send_file(target) # 直接用已验证的路径
send_file(Path) 会根据扩展名自动推断 MIME type,无需额外处理。
R2. 路径安全检查:用 ConfinedDir,禁止 str.startswith
原因:str(path).startswith(str(root)) 存在前缀碰撞缺陷(如 /workspace vs /workspace_evil)。
# ❌ BAD
if not str(resolved).startswith(str(root_resolved) + os.sep):
raise ValueError("escape")
# ✅ GOOD — 统一走 ConfinedDir,内部使用 Path.is_relative_to()
jail = ConfinedDir(root_resolved, mkdir=False)
target = jail.resolve(user_input)
R3. Agent 工具复用 Workspace.confined_*
原因:Agent 工具参数由 LLM 生成,必须视为间接用户输入。不要在工具内手写 Path(root) / rel_path 或 resolve() + relative_to();入口处复用 Workspace 暴露的 ConfinedDir。
# ❌ BAD — 手写路径拼接和校验
def _tool_read_file(self, args, workspace_path):
target = (workspace_path / rel_path).resolve()
target.relative_to(workspace_path)
# ✅ GOOD — 入口拿到 ConfinedDir,工具只调用 jail.resolve()
def _execute_tool(self, name, args):
workspace_jail = self.workspace.confined_root
scratch_jail = self.workspace.confined_scratch
return self._tool_read_file(args, workspace_jail)
def _tool_read_file(self, args, workspace_jail):
target = workspace_jail.resolve(args.get("path", ""))
R4. 优先使用 ConfinedDir,禁止裸路径拼接
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.
- 2d ago First seen · 161 lines · 50 tokens per session scan A cb98e8c0287a
path-safety is a skill published in the GitHub repository microsoft/data-formulator (17,048 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 1,727 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…