Skills/ClawHub/other-openclaw-skills

other-openclaw-skills@1.0.0

CAUTION· install only

Publisher claims: "Root entry skill for Meitu capabilities. Routes requests to scene skills (meitu-poster, meitu-stickers, meitu-visual-me, meitu-product-swap, meitu-video-danc..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher dongjie-oss · publishing for 154 daysInstalls 533Last detonated 22 h ago

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-13 and scored it 74/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Destructive file system command detected; Destructive file system command detected. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

LOW
Unpinned dependencySKILL.md:130 · Unpinned dependencynpm install -g meitu-cli@latest --forceFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06
LOW
Unpinned dependencymeitu-tools/SKILL.md:97 · Unpinned dependencynpm install -g meitu-cli@latestFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06
LOW
Unpinned dependencySKILL.md:202 · Unpinned dependency- CLI repair/upgrade is manual and user-driven: `npm install -g meitu-cli@latest`Fix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06
HIGH
Access to sensitive file pathsmeitu-tools/scripts/lib/input.js:143 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreturn { ...env, ...bridged };Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Destructive file system command detectedskills/meitu-upscale/SKILL.md:95 · Destructive file system command detected临时文件完成后清理:`rm -f /tmp/meitu-upscale-input.*`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Unpinned dependencymeitu-tools/SKILL.md:67 · Unpinned dependencynpm install -g meitu-cli@latest --forceFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06
LOW
Unpinned dependencymeitu-tools/SKILL.md:60 · Unpinned dependencynpm install -g meitu-cli@latestFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06
LOW
Unpinned dependencySKILL.md:123 · Unpinned dependencynpm install -g meitu-cli@latestFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06
HIGH
Destructive file system command detectedskills/meitu-image-fix/SKILL.md:126 · Destructive file system command detected中间文件**必须**存放在 `/tmp/` 或系统临时目录,**禁止**存入 skill 文件夹或源文件所在目录。管线完成后清理:`rm -f /tmp/meitu-fix-step*.{ext}`。Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Auto-update or dynamic fetch configurationmeitu-tools/scripts/lib/updater.js:146 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeconst enabled = envBool("MEITU_AUTO_UPDATE", true);Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagemeitu-tools/SKILL.md:82 · npx invocation of non-well-known package — may execute untrusted codenpx -y skills add https://github.com/meitu/meitu-skills --yesFix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Unpinned dependencymeitu-tools/SKILL.md:187 · Unpinned dependencynpm install -g meitu-cli@latestFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06
LOW
Unpinned dependencymeitu-tools/scripts/run_command.js:59 · Unpinned dependency" npm install -g meitu-cli@latest",Fix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06
LOW
Unpinned dependencymeitu-tools/SKILL.md:104 · Unpinned dependencynpm install -g meitu-cli@latest --forceFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06
LOW
Unpinned dependencymeitu-tools/scripts/run_command.js:70 · Unpinned dependency"请手动执行 'npm install -g meitu-cli@latest';如安装时报 EEXIST 或已有同名二进制冲突,可执行 'npm install -g meitu-cli@latest --force';随后执行 'meitu --version' 确认运行时可用后重试。",Fix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06
LOW
Refusal suppressionskills/meitu-visual-me/references/workflows.md:23 · Refusal suppression — attempting to prevent safety responses · informational: not an instruction file**Principle: Read whatever is available; if missing, ask or skip. Never refuse to generate due to missing data.**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectionskills/meitu-visual-me/references/channel-presets.md:23 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file| Wallpaper (desktop) | 16:9 | 2560x1440 | Desktop wallpaper | Avoid content in bottom-right corner (icon overlap) |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈31,638 tok
15 files · 54 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

6 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim dongjie-oss: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Unpinned dependencies≈ +4 on the totalPin exact versions (and ideally hashes) in package.json, requirements or the install script so the bundle cannot change under you.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  6. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim dongjie-ossPropose a patch to the maintainer