Skills/ClawHub/auto-domain

auto-domain@1.0.0

BLOCKED· install only

Publisher claims: "当用户说"启动项目"、"给项目一个公网域名"、"start tunnel"、"expose my project"、 "让项目可以公网访问"、"start my project with a public URL" 时自动触发。 无需用户做任何操作:自动检测项目目录和端口,修复环境,启动 tunnel, 直接返回..." Observed in sandbox: sends data to release-assets.githubusercontent.com.

Registry ClawHubPublisher changfenghu · publishing for 260 daysInstalls 720Last detonated 1 h ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
7 of 7 bundled scripts 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 2026-11-18 and scored it 45/100 (Blocked). Do not install it: the sandbox observed behaviour consistent with credential theft, exfiltration or persistence. Notable findings: Access to sensitive file paths; HTTP URL with a raw public IP address; Agent configured for autonomous execution without human approval. Summary: sends data to release-assets.githubusercontent.com.

Behavior trace

Honeypot run · 3 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.9snetworkCONNECT tcp://github.com:443
0.9snetworkCONNECT tcp://release-assets.githubusercontent.com:443 · not in the allow-list, refused
0.9sprocessexec /usr/bin/dirname
0.9sprocessexec /usr/bin/cp
0.9sprocessexec /usr/bin/chmod
0.9sprocessexec /tmp/ks-detonate-jjWgYH/scripts/home/work/acme-api/.claude/skills/auto-domain/scripts/check_env.sh
0.9sprocessexec /usr/bin/grep
0.9sprocessexec /usr/bin/basename
0.9sprocessexec /usr/bin/id
0.9sprocessexec /usr/bin/tr
0.9sprocessexec /usr/bin/sed
0.9sprocessexec /usr/bin/awk
0.9sprocessexec /usr/bin/cksum
0.9sprocessexec /usr/bin/mkdir
0.9sprocessexec /usr/bin/uname
0.9sprocessexec /usr/bin/rm
0.9sprocessexec /usr/bin/curl
0.9sprocessexited 22: curl: (22) The requested URL returned error: 403
0.9sprocessbundled script run in the sandbox with no arguments
0.9sprocessexited 1:
0.9sprocessbundled script run in the sandbox with no arguments
0.9sprocessexited 1:
0.9sprocessbundled script run in the sandbox with no arguments · not named in the instructions
1.0sprocessexec /usr/bin/dirname
1.0sprocessexec /usr/bin/cp
1.0sprocessexec /usr/bin/chmod
1.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
1.7snetworkCONNECT tcp://github.com:443
1.7snetworkCONNECT tcp://release-assets.githubusercontent.com:443 · not in the allow-list, refused
1.7sprocessexec /usr/bin/dirname
1.7sprocessexec /usr/bin/diff
1.7sprocessexec /tmp/ks-detonate-jjWgYH/scripts/home/work/acme-api/.claude/skills/auto-domain/scripts/check_env.sh
1.7sprocessexec /usr/bin/grep
1.7sprocessexec /usr/bin/basename
1.7sprocessexec /usr/bin/id
1.7sprocessexec /usr/bin/tr
1.7sprocessexec /usr/bin/sed
1.7sprocessexec /usr/bin/awk
1.7sprocessexec /usr/bin/cksum
1.7sprocessexec /usr/bin/mkdir
1.7sprocessexec /usr/bin/uname
1.7sprocessexec /usr/bin/rm
1.7sprocessexec /usr/bin/curl
1.7sprocessexited 22: curl: (22) The requested URL returned error: 403
1.7sprocessbundled script run in the sandbox with no arguments · not named in the instructions
1.7sprocessexec /usr/bin/dirname
1.7sprocessexec /tmp/ks-detonate-jjWgYH/scripts/home/work/acme-api/.claude/skills/auto-domain/scripts/install_project_tunnel.sh
1.7sprocessexited 126: ./scripts/start_project_tunnel.sh: line 25: /tmp/ks-detonate-jjWgYH/scripts/home/work/acme-api/.claude/skills/auto-domain/scripts/install_project_tunnel.sh: Permission denied
1.7sprocessbundled script run in the sandbox with no arguments
2.4snetworkCONNECT tcp://github.com:443
2.4snetworkCONNECT tcp://release-assets.githubusercontent.com:443 · not in the allow-list, refused
2.4sprocessexec /usr/bin/basename
2.4sprocessexec /usr/bin/id
2.4sprocessexec /usr/bin/tr
2.4sprocessexec /usr/bin/sed
2.4sprocessexec /usr/bin/cksum
2.4sprocessexec /usr/bin/awk
2.4sprocessexec /usr/bin/mkdir
2.4sprocessexec /usr/bin/uname
2.4sprocessexec /usr/bin/rm
2.4sprocessexec /usr/bin/curl
2.4sprocessexited 22: curl: (22) The requested URL returned error: 403
2.4sprocess7 of 7 bundled scripts run with no arguments
2.5sprocessscript backend runs setup only
2.5sprocessscript backend runs setup only
2.5sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsassets/project-tunnel.sh:22 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- PROJECT_PORT: .tunnel-port > .env.local/.env PORT= > 3000Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
HTTP URL with a raw public IP addressassets/project-tunnel.sh:29 · HTTP URL with a raw public IP address — a hard-coded destination that domain-based monitoring cannot name- CONTROL_API_BASE=http://152.32.214.95:3002/controlFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
CRITICAL
Agent configured for autonomous execution without human approvalagents/openai.yaml:7 · Agent configured for autonomous execution without human approvalSteps (execute autonomously, no user interaction needed):Fix: Declare and request only the permissions the task needs.
AST02
HIGH
HTTP URL with a raw public IP addressassets/project-tunnel.sh:772 · HTTP URL with a raw public IP address — a hard-coded destination that domain-based monitoring cannot nameAGENT_ROUTE_SYNC_URL="${AGENT_ROUTE_SYNC_URL:-http://152.32.214.95/_tunnel/agent/routes}"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Access to sensitive file pathsassets/project-tunnel.sh:697 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesPROJECT_PORT="$(port_from_file "${PROJECT_DIR}/.env" || true)"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
HTTP URL with a raw public IP addressassets/project-tunnel.sh:717 · HTTP URL with a raw public IP address — a hard-coded destination that domain-based monitoring cannot nameCONTROL_API_BASE="${CONTROL_API_BASE:-http://152.32.214.95:3002/control}"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Access to sensitive file pathsassets/project-tunnel.sh:695 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesPROJECT_PORT="$(port_from_file "${PROJECT_DIR}/.env.local" || true)"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commandscripts/fix_env.sh:39 · Privileged sudo command — agent may execute with elevated privilegeslsof) sudo apt-get install -y lsof ;;Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandassets/project-tunnel.sh:995 · File permission modification command — agent changes file ownership/permissionschmod +x "${MACHINE_AGENT_RUNNER}"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Privileged sudo commandscripts/fix_env.sh:38 · Privileged sudo command — agent may execute with elevated privilegescurl) sudo apt-get install -y curl ;;Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandscripts/fix_env.sh:40 · Privileged sudo command — agent may execute with elevated privileges*) sudo apt-get install -y "$tool" ;;Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandassets/project-tunnel.sh:571 · Process kill command — agent can terminate processeskill "${pid}" >/dev/null 2>&1 || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandassets/project-tunnel.sh:574 · Process kill command — agent can terminate processeskill -9 "${pid}" >/dev/null 2>&1 || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
URL using a raw public IP addressassets/project-tunnel.sh:772 · URL using a raw public IP address — may bypass domain-based filteringAGENT_ROUTE_SYNC_URL="${AGENT_ROUTE_SYNC_URL:-http://152.32.214.95/_tunnel/agent/routes}"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using a raw public IP addressassets/project-tunnel.sh:29 · URL using a raw public IP address — may bypass domain-based filtering- CONTROL_API_BASE=http://152.32.214.95:3002/controlFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Privileged sudo commandscripts/fix_env.sh:37 · Privileged sudo command — agent may execute with elevated privilegesnode|npm) sudo apt-get install -y nodejs npm ;;Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandassets/project-tunnel.sh:661 · File permission modification command — agent changes file ownership/permissionschmod +x "${AGENT_RUNNER}"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Direct script execution from GitHub raw URLscripts/fix_env.sh:21 · Direct script execution from GitHub raw URL — unverified code source/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Privileged sudo commandscripts/fix_env.sh:36 · Privileged sudo command — agent may execute with elevated privilegespython3) sudo apt-get install -y python3 ;;Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandscripts/auto_start.sh:55 · File permission modification command — agent changes file ownership/permissionschmod +x "${TARGET}"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/install_project_tunnel.sh:21 · File permission modification command — agent changes file ownership/permissionschmod +x "${TARGET_SCRIPT}"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandassets/project-tunnel.sh:596 · Process kill command — agent can terminate processeskill -9 "${pid}" >/dev/null 2>&1 || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandscripts/run_tunnel.sh:16 · File permission modification command — agent changes file ownership/permissionschmod +x "${TARGET}"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandassets/project-tunnel.sh:646 · File permission modification command — agent changes file ownership/permissionschmod +x "${APP_RUNNER}"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandassets/project-tunnel.sh:593 · Process kill command — agent can terminate processeskill "${pid}" >/dev/null 2>&1 || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandassets/project-tunnel.sh:560 · Process kill command — agent can terminate processeskill -0 "${pid}" >/dev/null 2>&1Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
URL using a raw public IP addressassets/project-tunnel.sh:717 · URL using a raw public IP address — may bypass domain-based filteringCONTROL_API_BASE="${CONTROL_API_BASE:-http://152.32.214.95:3002/control}"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File permission modification commandassets/project-tunnel.sh:553 · File permission modification command — agent changes file ownership/permissionschmod +x "${AGENT_BIN}" || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈280 tok
1 file · 9 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

35 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. 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.
  2. Agent configured for autonomous execution without human approval≈ +9 on the totalDeclare and request only the permissions the task needs.
  3. Unclaimed publisher≈ +8 on the totalClaim changfenghu: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. 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.
  5. HTTP URL with a raw public IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  6. Privileged sudo command≈ +4 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 changfenghuPropose a patch to the maintainer