Skills/ClawHub/gateway-config-guardian

gateway-config-guardian@1.6.3

VERIFIED· install only

Publisher claims: "Three-layer protection for the OpenClaw gateway: real-time config monitoring with auto-rollback, systemd crash recovery, and tiered notifications via Feishu/..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher dios-man · publishing for 233 daysInstalls 1,518Last detonated 1 h ago
$clawhub install gateway-config-guardian
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
4 of 4 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 81/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 15 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.0sprocessexec /usr/bin/dirname
0.0sprocessbundled script run in the sandbox with no arguments
15sfilesystemread ~/.openclaw/openclaw.json outside project
15sfilesystemwrote ~/.openclaw/workspace/memory/2026-11-18.md
15sprocessexec /usr/bin/dirname
15sprocessexec /usr/bin/tee
15sprocessexec /usr/bin/flock
15sprocessexec /usr/bin/ls
15sprocessexec /usr/bin/grep
15sprocessexec /usr/bin/tail
15sprocessexec /tmp/ks-detonate-PIR6er/scripts/home/.npm-global/bin/openclaw
15sprocessexec /usr/local/bin/openclaw
15sprocessexec /app/apps/web/node_modules/.bin/openclaw
15sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/openclaw
15sprocessexec /app/node_modules/.bin/openclaw
15sprocessexec /pnpm/openclaw
15sprocessexec /usr/local/sbin/openclaw
15sprocessexec /usr/sbin/openclaw
15sprocessexec /usr/bin/openclaw
15sprocessexec /sbin/openclaw
15sprocessexec /bin/openclaw
15sprocessexec /usr/bin/mkdir
15sprocessbundled script run in the sandbox with no arguments
15sfilesystemread ~/.openclaw/openclaw.json outside project
15sfilesystemwrote ~/.openclaw/workspace/memory/2026-11-18.md
15sprocessexec /usr/bin/dirname
15sprocessexec /usr/bin/tee
15sprocessexec /usr/bin/flock
15sprocessexec /usr/bin/ls
15sprocessexec /usr/bin/mkdir
15sprocessexec /usr/bin/grep
15sprocessexec /usr/bin/tail
15sprocessexec /tmp/ks-detonate-PIR6er/scripts/home/.npm-global/bin/openclaw
15sprocessexec /usr/local/bin/openclaw
15sprocessexec /app/apps/web/node_modules/.bin/openclaw
15sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/openclaw
15sprocessexec /app/node_modules/.bin/openclaw
15sprocessexec /pnpm/openclaw
15sprocessexec /usr/local/sbin/openclaw
15sprocessexec /usr/sbin/openclaw
15sprocessexec /usr/bin/openclaw
15sprocessexec /sbin/openclaw
15sprocessexec /bin/openclaw
15sprocessexited 1:
15sprocessbundled script run in the sandbox with no arguments
15sprocessexec /usr/bin/dirname
15sprocessexec /usr/bin/tee
15sprocess4 of 4 bundled scripts run with no arguments
15sprocessscript backend runs setup only
15sprocessscript backend runs setup only
15sprocessno install scripts to re-run

Static findings

HIGH
Privileged sudo commandSKILL.md:45 · Privileged sudo command — agent may execute with elevated privilegessudo apt-get install -y inotify-tools 2>/dev/null || apt-get install -y inotify-tools 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandSKILL.md:141 · File permission modification command — agent changes file ownership/permissionschmod +x "$SKILL_DIR/pre-stop.sh"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandSKILL.md:140 · File permission modification command — agent changes file ownership/permissionschmod +x "$SKILL_DIR/gateway-recovery.sh"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Privileged sudo commandSKILL.md:48 · Privileged sudo command — agent may execute with elevated privilegesIf `apt-get` fails (no sudo), ask the user to run: `sudo apt-get install -y inotify-tools`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandSKILL.md:139 · File permission modification command — agent changes file ownership/permissionschmod +x "$SKILL_DIR/config-watcher.sh"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈2,516 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.