Skills/ClawHub/skillhub-auto-installer

skillhub-auto-installer@1.0.2

CAUTION· static only

Publisher claims: "搜索 Skillhub 技能市场,发现可用技能。 此技能仅提供搜索功能,不执行任何安装或本地文件操作。 关键词: skillhub, 搜索技能, findskill, 技能发现, 技能市场" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher jiayao0810 · publishing for 232 daysInstalls 923Last detonated 2 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 2026-11-19 and scored it 52/100 (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 command against a filesystem root or device; Destructive file system command detected; Destructive file system command detected. 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

CRITICAL
Destructive command against a filesystem root or devicescripts/security-check.sh:120 · Destructive command against a filesystem root or deviceDANGEROUS=$(grep -rE "(rm -rf /|rm -rf \*|> /etc/|chmod 777 /|curl.*\|.*sh|wget.*\|.*sh)" "$TARGET_SKILL_DIR/scripts/" 2>/dev/null | grep -v "^#" || true)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedscripts/secure-install.sh:107 · Destructive file system command detectedSUSPICIOUS=$(grep -r "rm -rf /\|curl.*|.*sh\|wget.*|.*sh\|bash -c.*\$(curl" "$SKILLS_DIR/$SKILL_NAME/scripts/" 2>/dev/null || true)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedscripts/security-check.sh:120 · Destructive file system command detectedDANGEROUS=$(grep -rE "(rm -rf /|rm -rf \*|> /etc/|chmod 777 /|curl.*\|.*sh|wget.*\|.*sh)" "$TARGET_SKILL_DIR/scripts/" 2>/dev/null | grep -v "^#" || true)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagescripts/search.sh:24 · npx invocation of non-well-known package — may execute untrusted codeSKILLS_API_URL="$API_URL" npx -y skills find "$QUERY" --limit "$LIMIT" 2>/dev/null || {Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/pre-install-check.sh:121 · npx invocation of non-well-known package — may execute untrusted codeecho " SKILLS_API_URL=https://skills.volces.com/v1 npx -y skills add \\"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/pre-install-check.sh:49 · npx invocation of non-well-known package — may execute untrusted codecheck_dependency npxFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:52 · npx invocation of non-well-known package — may execute untrusted codeSKILLS_API_URL=https://skills.volces.com/v1 npx -y skills find "关键词"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/secure-install.sh:72 · npx invocation of non-well-known package — may execute untrusted codeSKILLS_API_URL=https://skills.volces.com/v1 npx -y skills add "$URL" -s "$SKILL_NAME" -a openclaw -y --copyFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/pre-install-check.sh:89 · npx invocation of non-well-known package — may execute untrusted codeecho " SKILLS_API_URL=https://skills.volces.com/v1 npx -y skills add https://skills.volces.com/skills/clawhub/poolguy24 -s skillsentry -a openclaw -y --copy"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/pre-install-check.sh:50 · npx invocation of non-well-known package — may execute untrusted codeecho " ✅ Node.js 和 npx 已安装"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskillhub-auto-installer/SKILL.md:52 · npx invocation of non-well-known package — may execute untrusted codeSKILLS_API_URL=https://skills.volces.com/v1 npx -y skills find "关键词"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/install.sh:40 · npx invocation of non-well-known package — may execute untrusted codeSKILLS_API_URL=https://skills.volces.com/v1 npx -y skills add "$URL" -s "$SKILL_NAME" -a openclaw -y --copyFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskillhub-auto-installer/SKILL.md:55 · npx invocation of non-well-known package — may execute untrusted codeSKILLS_API_URL=https://skills.volces.com/v1 npx -y skills add <URL> -s <skill-name> -a openclaw -y --copyFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/secure-install.sh:46 · npx invocation of non-well-known package — may execute untrusted codeecho " 建议先安装: npx skills add ... skillsentry"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskillhub-auto-installer/scripts/search.sh:24 · npx invocation of non-well-known package — may execute untrusted codeSKILLS_API_URL="$API_URL" npx -y skills find "$QUERY" --limit "$LIMIT" 2>/dev/null || {Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/security-check.sh:56 · npx invocation of non-well-known package — may execute untrusted codeecho " SKILLS_API_URL=https://skills.volces.com/v1 npx -y skills add \\"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:55 · npx invocation of non-well-known package — may execute untrusted codeSKILLS_API_URL=https://skills.volces.com/v1 npx -y skills add <URL> -s <skill-name> -a openclaw -y --copyFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandscripts/security-check.sh:120 · File permission modification command — agent changes file ownership/permissionsDANGEROUS=$(grep -rE "(rm -rf /|rm -rf \*|> /etc/|chmod 777 /|curl.*\|.*sh|wget.*\|.*sh)" "$TARGET_SKILL_DIR/scripts/" 2>/dev/null | grep -v "^#" || true)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈490 tok
2 files · 10 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

28 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  2. Unclaimed publisher≈ +8 on the totalClaim jiayao0810: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim jiayao0810Propose a patch to the maintainer