SKILLEMALL.ai
GitHub ↗ RU Sign in

FF fluxmount

FluxMount - 让 macOS 自由读写外接 NTFS 硬盘，傻瓜式、一次到位、插上即用、不再复发。当用户把 NTFS 格式的移动硬盘或 SSD 接到 Mac 却无法写入或复制文件、抱怨各种插件都传不进去、问 Mac 怎么往 NTFS 盘里写文件、或想要开机与热插拔自动可读写挂载时使用。覆盖国内网络典型坑（GitHub 被墙、Homebrew Tier-3 无预编译包、新版 Clang 编译报错、launchctl 弃用、沙箱禁 sudo），并提供一键安装、健康自检与干净卸载。作者 张昌宇 (Changyu Zhang)。

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: hackerFish v0.1.0 MIT-0 19 files · 5 scripts body ≈ 719 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

FluxMount - 让 macOS 自由读写外接 NTFS 硬盘，傻瓜式、一次到位、插上即用、不再复发。当用户把 NTFS 格式的移动硬盘或 SSD 接到 Mac 却无法写入或复制文件、抱怨各种插件都传不进去、问 Mac 怎么往 NTFS…

As a process F 35/100 · Will not run — References files that are not bundled: scripts/mount-ntfs-rw, scripts/ntfs-automount

ProcedureGitHubWriting and documentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
F
26/100
safety, quality, tests
Safety 60%
0
Quality 40%
64
Run on models
none yet
Process rating
F
35/100
Will not run
References files that are not bundled: scripts/mount-ntfs-rw, scripts/ntfs-automount
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  3. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 21

  • high Dangerous commands cmd-persistence scripts/install.sh:203
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl bootstrap "gui/$(id -u)" "$AGENT_PLIST" 2>/dev/null && echo "  ✅ 自动挂载代理已注册(开机+热插拔)" || echo "  ⚠️  代理注册需在图形会话终端执行，请在本机终端重跑一次本脚本"
Medium and low: 20
  • medium Dangerous commands cmd-persistence references/troubleshooting.md:58
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    ### 8. `launchctl load` 在 macOS 15 失效
    quoted
  • medium Dangerous commands cmd-persistence references/troubleshooting.md:60
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    - 现象: `launchctl list` 查不到、`launchctl load` 报 Input/output error。
    quoted
  • medium Dangerous commands cmd-persistence references/troubleshooting.md:61
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    - 根因: macOS 15 (Sequoia) 已弃用 `launchctl load`，且远程/沙箱环境会拦截写类 launchctl。
    quoted
  • medium Dangerous commands cmd-persistence references/troubleshooting.md:62
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    - 解法: 用现代方式 `launchctl bootout gui/$(id -u)/LABEL` 再 `launchctl bootstrap gui/$(id -u) ~/Library/LaunchAgents/xxx.plist`，且**必须在图形登录会话的真实终端**执行（WorkBuddy 沙箱内的 Bash 无法替你注册）。
    quoted
  • medium Dangerous commands cmd-persistence SAFETY.md:14
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation table row)
    | 开机/热插拔代理 | `~/Library/LaunchAgents/com.changyu.fluxmount.plist` | 自动挂载触发器（覆盖前会备份） |
    table
  • medium Dangerous commands cmd-persistence scripts/install.sh:23
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    AGENT_PLIST="$HOME/Library/LaunchAgents/$AGENT_LABEL.plist"
    code literal
  • medium Dangerous commands cmd-quarantine-file scripts/install.sh:120
    Removes the macOS quarantine flag from one file (usual for a downloaded CLI; make sure the file is the intended binary)
    xattr -d com.apple.quarantine "$dmg" 2>/dev/null || true
  • medium Dangerous commands cmd-privilege scripts/install.sh:168
    Privilege escalation / world-writable permissions
    sudo cp "$(dirname "$0")/mount-ntfs-rw" "$MOUNT_SH"
  • medium Dangerous commands cmd-privilege scripts/install.sh:169
    Privilege escalation / world-writable permissions
    sudo cp "$(dirname "$0")/ntfs-automount" "$AUTO_SH"
  • medium Dangerous commands cmd-privilege scripts/install.sh:170
    Privilege escalation / world-writable permissions
    sudo chmod +x "$MOUNT_SH" "$AUTO_SH"
  • medium Dangerous commands cmd-privilege scripts/install.sh:174
    Privilege escalation / world-writable permissions
    echo "$USER ALL=(root) NOPASSWD: $MOUNT_SH" | sudo tee "$SUDOERS" >/dev/null
  • medium Dangerous commands cmd-privilege scripts/install.sh:175
    Privilege escalation / world-writable permissions
    sudo chmod 440 "$SUDOERS"
  • medium Dangerous commands cmd-persistence scripts/install.sh:179
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    OLD_AGENT="$HOME/Library/LaunchAgents/com.user.ntfs-automount.plist"
    code literal
  • medium Dangerous commands cmd-persistence scripts/uninstall.sh:13
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    AGENT_PLIST="$HOME/Library/LaunchAgents/$AGENT_LABEL.plist"
    code literal
  • medium Dangerous commands cmd-privilege scripts/uninstall.sh:31
    Privilege escalation / world-writable permissions
    sudo rm -f "$STATE_FILE" 2>/dev/null || true
  • medium Dangerous commands cmd-privilege scripts/uninstall.sh:42
    Privilege escalation / world-writable permissions
    sudo rm -f "$SUDOERS"
  • medium Dangerous commands cmd-privilege scripts/uninstall.sh:49
    Privilege escalation / world-writable permissions
    sudo cp -a "$bak" "$f" 2>/dev/null && echo "  ♻️  已还原安装前文件: $f" || echo "  ⚠️  还原失败: $f"
  • medium Dangerous commands cmd-privilege scripts/uninstall.sh:51
    Privilege escalation / world-writable permissions
    sudo rm -f "$f" 2>/dev/null && echo "  🗑️  已移除: $f" || echo "  ⚠️  移除失败(可能需手动): $f"
  • medium Dangerous commands cmd-persistence SKILL.md:84
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    > 踩坑经验（已固化到 troubleshooting.md）：GitHub 被墙用国内镜像；Homebrew `brew install ntfs-3g` 在 2026 年 macOS 15 Intel 上因 Tier-3 无 bottle 失败，应改 `ntfs-3g-mac`；新版 Xcode/Clang 把隐式函数声明当硬错误导致源码编译失败；`launchctl load` 在 macO
    quoted
  • low Dangerous commands cmd-privilege references/troubleshooting.md:31
    Privilege escalation / world-writable permissions (quoted — discussed, not commanded)
    - 解法: `sudo chown -R $USER /usr/local/share/man/man8 && chmod u+w /usr/local/share/man/man8`，再重跑。
    quoted

Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: scripts/mount-ntfs-rw
  • warning missing-ref reference to a missing file: scripts/ntfs-automount
  • note frontmatter-key unknown frontmatter key "agent_created"

Process rating: all ten parameters 35/100

Will not run. References files that are not bundled: scripts/mount-ntfs-rw, scripts/ntfs-automount
  • 0Tools and files. 2 referenced file(s) missing: scripts/mount-ntfs-rw, scripts/ntfs-automount
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 100Steps. 20 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 719 tokens
  • 100Running it twice. No mutating operations

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -31 of 3 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 268: enough signal without eating the budget
  • +4Structure: 10 headings
  • +3Step-by-step instructions: 20 items
  • +4Has examples (3 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.

External checks

ClawHub: suspicious
FluxMount has a real NTFS-write purpose, but it installs privileged disk-mounting automation with passwordless sudo and startup/hot-plug persistence by default.
LLM: suspicious (high) · 12 Aug 2026