Skills/ClawHub/skill-admission-gate

skill-admission-gate@1.0.8

CAUTION

Publisher claims: "Scan a skill or plugin before installation and block destructive commands, remote execution, data exfiltration, prompt injection, obfuscated payloads and scope overreach. 技能上架安全闸门——一个技能/插件在安装或上架前，先跑确定性安全审查：查破坏性命令、远程执行、数据外泄、提示注入、隐蔽行为、混淆载荷与作用域越界，产出「分级发现 + 闸门判定 + 包指纹证据」。当需要审查第三方 skill、安装来源不明的技能、给自研技能做发布前安检、做供应链安全评估、或需要出具"该包未被篡改且已评估风险"的证据时调用。核心三件事：①按规则集扫全部文件并分级（BLOCK/WARN）②支持"已接受风险"声明（.admission-allow.json，须署名留痕）③输出包指纹与文件哈希作为"有证"产物。触发词：技能安全、审查 skill、安装前检查、恶意技能、skill 安全扫描、上架闸门、供应链安全、这个技能安全吗、第三方技能、能不能装、木马、后门、提示注入。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher zhaoxinghua09-cell · joined 10 days agoInstalls 270Last detonated 49 min ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-06 and scored it 61/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive file system command detected; Access to sensitive file paths; Access to sensitive file paths. 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

HIGH
Destructive file system command detectedSKILL.md:136 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsSKILL.md:140 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Remote installer piped to shellSKILL.md:137 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Access to sensitive file pathsscripts/scan_skill.py:37 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Prompt injection attemptSKILL.md:141 · Prompt injection attempt — 'ignore previous instructions'Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathsSKILL.md:275 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/scan_skill.py:35 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Remote installer piped to shellSKILL.md:272 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Destructive file system command detectedSKILL.md:271 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈3,814 tok
2 files · 6 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

19 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Asks the agent to act silently or skip confirmation≈ +8 on the totalRemove "do not tell the user", "without asking", "disable safety" and similar. An agent skill should never ask to be invisible.
  3. Unclaimed publisher≈ +8 on the totalClaim zhaoxinghua09-cell: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. 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.
  6. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim zhaoxinghua09-cellPropose a patch to the maintainer