Skills/ClawHub/fortress-agent-suite

fortress-agent-suite@1.0.1

CAUTION· install only

Publisher claims: "Fortress Agent Suite provides self-healing, health monitoring, automated maintenance, and LLM model management for OpenClaw agents in production." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher kienphan91 · publishing for 228 daysInstalls 889Last detonated 2 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 2026-11-19 and scored it 72/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: OS command execution function call detected; OS command execution function call detected; OS command execution function call detected. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 2 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 1: PermissionError: [Errno 13] Permission denied: '/root/.openclaw/secrets/openrouter.token'
0.4sprocessbundled script run in the sandbox with no arguments
0.7sprocessexited 1: PermissionError: [Errno 13] Permission denied: '/root/.openclaw/workspace/backups/config_20261119_224525'
0.7sprocessbundled script run in the sandbox with no arguments
0.8sprocessexec /app/apps/web/node_modules/.bin/openclaw
0.8sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/openclaw
0.8sprocessexec /app/node_modules/.bin/openclaw
0.8sprocessexec /pnpm/openclaw
0.8sprocessexec /usr/local/sbin/openclaw
0.8sprocessexec /usr/local/bin/openclaw
0.8sprocessexec /usr/sbin/openclaw
0.8sprocessexec /usr/bin/openclaw
0.8sprocessexec /sbin/openclaw
0.8sprocessexec /bin/openclaw
0.8sprocessexited 1: PermissionError: [Errno 13] Permission denied: '/root/.openclaw/telegram_config'
0.8sprocessbundled script run in the sandbox with no arguments · not named in the instructions
1.0sprocessexited 1: PermissionError: [Errno 13] Permission denied: '/root/.openclaw/workspace/backups'
1.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
1.2sprocessexited 1: PermissionError: [Errno 13] Permission denied: '/root/.openclaw/logs'
1.2sprocessbundled script run in the sandbox with no arguments
1.4sprocessexited 1: ModuleNotFoundError: No module named 'psutil'
1.4sprocessbundled script run in the sandbox with no arguments
1.5sprocessexited 1: PermissionError: [Errno 13] Permission denied: '/root/.openclaw/workspace/.git'
1.5sprocess7 of 7 bundled scripts run with no arguments
1.5sprocessscript backend runs setup only
1.5sprocessscript backend runs setup only
1.5sprocessno install scripts to re-run

Static findings

CRITICAL
OS command execution function call detectedscripts/self-healing/health_check.py:13 · OS command execution function call detectedos.system(f"curl -s 'https://api.telegram.org/bot{token}/sendMessage?chat_id={chat_id}&text={urllib.parse.quote_plus(msg)}' > /dev/null")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
OS command execution function call detectedscripts/self-healing/restore.py:12 · OS command execution function call detectedos.system('openclaw gateway restart')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
OS command execution function call detectedscripts/self-healing/self_improver.py:96 · OS command execution function call detectedos.system(f"curl -s 'https://api.telegram.org/bot{token}/sendMessage?chat_id={chat_id}&text={urllib.parse.quote_plus(msg)}' > /dev/null")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
OS command execution function call detectedscripts/model_manager/manager.py:21 · OS command execution function call detectedos.system('openclaw gateway restart')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
OS command execution function call detectedscripts/self-healing/self_improver.py:114 · OS command execution function call detectedresult = os.popen(f"openclaw skills install {slug} 2>&1").read()Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
OS command execution function call detectedscripts/self-healing/system_watchdog.py:11 · OS command execution function call detectedos.system('sync; echo 3 > /proc/sys/vm/drop_caches')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
OS command execution function call detectedscripts/self-healing/system_watchdog.py:7 · OS command execution function call detectedos.system('find /root/.openclaw/logs -name "*.log" -mtime +7 -delete')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/self-healing/workspace_watchdog.py:14 · Python subprocess execution detectedcron = subprocess.check_output(['crontab', '-l']).decode()Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Telegram Bot API URLscripts/self-healing/health_check.py:13 · Telegram Bot API URL — data will be sent to Telegramos.system(f"curl -s 'https://api.telegram.org/bot{token}/sendMessage?chat_id={chat_id}&text={urllib.parse.quote_plus(msg)}' > /dev/null")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedscripts/self-healing/health_check.py:17 · Python subprocess execution detectedsubprocess.check_call(['openclaw', 'gateway', 'status'], timeout=5)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/self-healing/workspace_watchdog.py:8 · Python subprocess execution detectedstatus = subprocess.check_output(['git', '-C', str(WORKSPACE), 'status', '--porcelain']).decode()Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
OS command execution function call detectedscripts/self-healing/workspace_watchdog.py:11 · OS command execution function call detectedos.system(f"git -C {WORKSPACE} add . && git -C {WORKSPACE} commit -m 'Auto-backup: {os.popen('date').read().strip()}'")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Telegram Bot API URLscripts/self-healing/self_improver.py:96 · Telegram Bot API URL — data will be sent to Telegramos.system(f"curl -s 'https://api.telegram.org/bot{token}/sendMessage?chat_id={chat_id}&text={urllib.parse.quote_plus(msg)}' > /dev/null")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
CRITICAL
OS command execution function call detectedscripts/self-healing/workspace_watchdog.py:18 · OS command execution function call detectedos.system(f"crontab -l | {{ cat; echo '*/30 * * * * /root/.openclaw/.venv/bin/python /root/.openclaw/scripts/self-healing/{r}'; }} | crontab -")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈274 tok
1 file · 13 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

8 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. OS command execution function call detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  2. Unclaimed publisher≈ +8 on the totalClaim kienphan91: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Telegram Bot API URL≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim kienphan91Propose a patch to the maintainer