Skills/ClawHub/nas-file-courier

nas-file-courier@1.0.0

CAUTION· static only

Publisher claims: "Search files on NAS (via rclone + Tailscale) and send to user via messaging API. Triggers on file search, find file, send file, 找文件, 发文件, NAS 查找, 下载文件." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher tecfancy · publishing for 251 daysInstalls 1,203Last detonated 1 h ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-17 and scored it 59/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; Destructive file system command detected; Authorization escalation language. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

HIGH
Privileged sudo commandSKILL.md:28 · Privileged sudo command — agent may execute with elevated privileges| sudo access | (for initial setup only) | Install rclone, fuse3, configure remotes |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedSKILL.md:211 · Destructive file system command detected🧹 清理: rm -f /tmp/openclaw/nas-courier/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:161 · Process kill command — agent can terminate processeskill $SERVE_PID 2>/dev/null # 如果使用了 Step 4bFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Authorization escalation languageSKILL.md:28 · Authorization escalation language| sudo access | (for initial setup only) | Install rclone, fuse3, configure remotes |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Destructive file system command detectedSKILL.md:162 · Destructive file system command detectedrm -f /tmp/openclaw/nas-courier/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandSKILL.md:40 · Privileged sudo command — agent may execute with elevated privileges| 权限 | 普通用户,无 sudo |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈1,308 tok
1 file · 5 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

21 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim tecfancy: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim tecfancyPropose a patch to the maintainer