Skills/ClawHub/skill-distributor

skill-distributor@1.0.0

BLOCKED· install only

Publisher claims: "一键将 Skill 分发到全平台。读取 SKILL.md → 生成各平台描述文案(GitHub/CocoLoop/SkillHub/SkillsBook/虾技市场/ClawHub)→ 生成社交推广文案(小红书/即刻/知乎/掘金)→ 输出到 distro/ 文件夹 → 可选 GitHub 推送。" Observed in sandbox: reads credential files, sends data to clawhub.ai.

Registry ClawHubPublisher gmf515 · publishing for 192 daysInstalls 724Last detonated 29 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
1 of 1 bundled script run with no arguments, with decoy credentials in the environment · 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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-22 and scored it 30/100 (Blocked). Do not install it: the sandbox observed behaviour consistent with credential theft, exfiltration or persistence. Summary: reads credential files, sends data to clawhub.ai.

Behavior trace

Honeypot run · 6 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
6.3sfilesystemread ~/work/acme-api/.npmrc · ~/.npmrc
6.3sfilesystemread ~/.npm/_logs · ~/.npm/_cacache/index-v5/bd/b7/857c28c9d64a6d56122957410244384c8deeb263e835436f9709446bacd3 · ~/.npm/_npx/ce38bf0ef4fd88c6/package.json · ~/.npm/_npx/ce38bf0ef4fd88c6/node_modules/.package-lock.json · ~/.npm/_npx/ce38bf0ef4fd88c6/npm-shrinkwrap.json · ~/.npm/_npx/ce38bf0ef4fd88c6/node_modules outside project
6.3sfilesystemwrote ~/.npm/_cacache/tmp/8e71a70d · ~/.npm/_cacache/index-v5/bd/b7/857c28c9d64a6d56122957410244384c8deeb263e835436f9709446bacd3 · ~/.npm/_cacache/tmp/582c2ae7 · ~/.npm/_cacache/tmp/6bc7057b · ~/.npm/_cacache/tmp/adea933c · ~/.npm/_cacache/tmp/6d77ff56
6.3snetworkCONNECT tcp://registry.npmjs.org:443
6.3snetworkCONNECT tcp://registry.npmjs.org:443
6.3snetworkCONNECT tcp://registry.npmjs.org:443
6.3snetworkCONNECT tcp://registry.npmjs.org:443
6.3snetworkCONNECT tcp://registry.npmjs.org:443
6.3snetworkCONNECT tcp://registry.npmjs.org:443
6.3snetworkCONNECT tcp://registry.npmjs.org:443
6.3snetworkCONNECT tcp://registry.npmjs.org:443
6.3snetworkCONNECT tcp://registry.npmjs.org:443
6.3snetworkCONNECT tcp://registry.npmjs.org:443
6.3snetworkCONNECT tcp://registry.npmjs.org:443
6.3snetworkCONNECT tcp://registry.npmjs.org:443
6.3snetworkCONNECT tcp://registry.npmjs.org:443
6.3snetworkCONNECT tcp://registry.npmjs.org:443
6.3snetworkCONNECT tcp://registry.npmjs.org:443
6.3snetworkCONNECT tcp://clawhub.ai:443 · not in the allow-list, refused
6.3sprocessexec /usr/bin/grep
6.3sprocessexec /usr/bin/sed
6.3sprocessexec /usr/bin/head
6.3sprocessexec /usr/bin/cut
6.3sprocessexec /usr/local/bin/npx
6.3sprocessexec /tmp/ks-detonate-AEVPYw/scripts/home/.npm/_npx/ce38bf0ef4fd88c6/node_modules/.bin/clawhub
6.3sprocessexec /tmp/ks-detonate-AEVPYw/scripts/home/.npm/_npx/ce38bf0ef4fd88c6/node_modules/.bin/git
6.3sprocessexec /tmp/ks-detonate-AEVPYw/scripts/home/work/acme-api/.claude/skills/skill-distributor/node_modules/.bin/git
6.3sprocessexec /tmp/ks-detonate-AEVPYw/scripts/home/work/acme-api/.claude/skills/node_modules/.bin/git
6.3sprocessexec /tmp/ks-detonate-AEVPYw/scripts/home/work/acme-api/.claude/node_modules/.bin/git
6.3sprocessexec /tmp/ks-detonate-AEVPYw/scripts/home/work/acme-api/node_modules/.bin/git
6.3sprocessexec /tmp/ks-detonate-AEVPYw/scripts/home/work/node_modules/.bin/git
6.3sprocessexec /tmp/ks-detonate-AEVPYw/scripts/home/node_modules/.bin/git
6.3sprocessexec /tmp/ks-detonate-AEVPYw/scripts/node_modules/.bin/git
6.3sprocessexec /tmp/ks-detonate-AEVPYw/node_modules/.bin/git
6.3sprocessexec /tmp/node_modules/.bin/git
6.3sprocessexec /node_modules/.bin/git
6.3sprocessexec /usr/local/lib/node_modules/npm/node_modules/@npmcli/run-script/lib/node-gyp-bin/git
6.3sprocessexec /app/apps/web/node_modules/.bin/git
6.3sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/git
6.3sprocessexec /app/node_modules/.bin/git
6.3sprocessexec /pnpm/git
6.3sprocessexec /usr/local/sbin/git
6.3sprocessexec /usr/local/bin/git
6.3sprocessexec /usr/sbin/git
6.3sprocessexec /usr/bin/git
6.3sprocessexited 1:
6.3sprocess1 of 1 bundled script run with no arguments
6.3sprocessscript backend runs setup only
6.3sprocessscript backend runs setup only
6.3sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagescripts/validate-skill.sh:92 · npx invocation of non-well-known package — may execute untrusted codeecho "✅ npx 可用(clawhub CLI)"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:193 · npx invocation of non-well-known package — may execute untrusted codenpx clawhub --workdir . skill publish . \Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/validate-skill.sh:98 · npx invocation of non-well-known package — may execute untrusted codeif npx clawhub whoami >/dev/null 2>&1; thenFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/validate-skill.sh:94 · npx invocation of non-well-known package — may execute untrusted codeecho "⚠️ npx 不可用,请安装 Node.js"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/validate-skill.sh:91 · npx invocation of non-well-known package — may execute untrusted codeif command -v npx >/dev/null 2>&1; thenFix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈1,500 tok
1 file · 17 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

50 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%

An override rule (credential_read_plus_egress) caps this verdict regardless of the score. The first item below has to go before anything else counts.

  1. Reads credential files≈ +27 on the totalThe sandbox saw reads under ~/.ssh, ~/.aws, ~/.npmrc, ~/.config or similar. Read only files inside the project, and only the ones the task needs.
  2. Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
  3. Unclaimed publisher≈ +8 on the totalClaim gmf515: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  5. 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 gmf515Propose a patch to the maintainer