FC lobsterguard

Bilingual security auditor for OpenClaw. 68 checks across 6 categories, 11 auto-fixes, OWASP Agentic AI Top 10 coverage, forensic detection, real-time threat interception, and guided hardening.

Not recommendedcritical or high security findings · low grade F

modbender/skill-library-mcp Agent Skills author: modbender MIT 17 files · 1 script body ≈ 1 673 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Bilingual security auditor for OpenClaw.

As a process C 60/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

Analyzer Telegram Docker Infrastructure AI and agents Securitytype and topics are labelled automatically from the skill text

Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode

JSON

Technical rating

29/100

safety, quality, tests

Safety 60%: 0
Quality 40%: 73
Run on models: none yet

Process rating

60/100

Has gaps

Result and completion w 14: 0
Inputs and preconditions w 11: 0
When it triggers w 12: 20

the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.

For the model run — optional

Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 52

high Exfiltration exfil-post-credential-file scripts/check.py:58

Uploads a credential/secret file to a remote endpoint (detector / deny-list definition)
```
r"curl.*-d.*\.env",                    # Credential exfiltration via curl
```
detector

Medium and low: 51

medium Dangerous commands cmd-persistence install.sh:201

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
```
su - "$OC_USER" -c "(crontab -l 2>/dev/null; echo '$CRON_LINE') | crontab -"
```
code literal
medium Dangerous commands cmd-persistence scripts/check.py:1558

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
```
("ls /etc/cron.daily/*backup* 2>/dev/null", "daily backup script"),
```
code literal
medium Dangerous commands cmd-persistence scripts/check.py:1793

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
```
("ls /etc/cron.d/ 2>/dev/null", "cron.d directory"),
```
code literal
medium Dangerous commands cmd-persistence scripts/check.py:1817

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (code comment)
```
# Check /etc/cron.d for unusual files
```
comment
medium Dangerous commands cmd-persistence scripts/check.py:1818

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
```
cron_d_stdout, _, _ = run_command("ls -la /etc/cron.d/ 2>/dev/null")
```
code literal
medium Dangerous commands cmd-pipe-to-shell scripts/check.py:4215

Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
```
"   curl -fsSL https://get.docker.com | sudo sh",
```
code literal
medium Dangerous commands cmd-pipe-to-shell scripts/check.py:4240

Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
```
"   curl -fsSL https://get.docker.com | sudo sh",
```
code literal
medium Dangerous commands cmd-persistence scripts/fix_engine.py:720

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
```
"command": "(crontab -l 2>/dev/null; echo '0 2 * * * ~/.openclaw/backup.sh') | crontab -",
```
code literal
medium Exfiltration exfil-webhook-url scripts/telegram_utils.py:60

Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
```
url = f"https://api.telegram.org/bot{bot_token}/sendMessage"
```
quoted
low Dangerous commands cmd-privilege docs/docker-setup-guide.md:35

Privilege escalation / world-writable permissions (documentation of a security skill)
```
sudo chmod a+r /etc/apt/keyrings/docker.gpg
```
security skill
low Dangerous commands cmd-privilege docs/docker-setup-guide.md:41

Privilege escalation / world-writable permissions (documentation of a security skill)
```
sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
```
security skill
low Dangerous commands cmd-privilege docs/docker-setup-guide.md:179

Privilege escalation / world-writable permissions (documentation of a security skill)
```
sudo bash install.sh
```
security skill
low Dangerous commands cmd-privilege install.sh:35

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
log_info "Uso: sudo bash install.sh"
```
code literal
low Dangerous commands cmd-cron-mention install.sh:198

Mentions editing / listing crontab (string literal in code, not executed)
```
if su - "$OC_USER" -c "crontab -l 2>/dev/null" | grep -q "cleanup.py"; then
```
code literal
low Dangerous commands cmd-cron-mention install.sh:201

Mentions editing / listing crontab (string literal in code, not executed)
```
su - "$OC_USER" -c "(crontab -l 2>/dev/null; echo '$CRON_LINE') | crontab -"
```
code literal
low Dangerous commands cmd-cron-mention install.sh:255

Mentions editing / listing crontab (string literal in code, not executed)
```
if su - "$OC_USER" -c "crontab -l 2>/dev/null" | grep -q "cleanup.py"; then
```
code literal
low Dangerous commands cmd-cron-mention install.sh:256

Mentions editing / listing crontab (detector / deny-list definition; string literal in code, not executed)
```
su - "$OC_USER" -c "crontab -l 2>/dev/null | grep -v cleanup.py | crontab -"
```
detectorcode literal
low Dangerous commands cmd-privilege install.sh:302

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
printf "  ${YELLOW}Desinstalar: sudo bash install.sh --uninstall${NC}\n\n"
```
code literal
low Dangerous commands cmd-privilege README.es.md:78

Privilege escalation / world-writable permissions (documentation of a security skill)
```
sudo bash install.sh
```
security skill
low Dangerous commands cmd-privilege README.es.md:94

Privilege escalation / world-writable permissions (documentation of a security skill)
```
sudo bash install.sh --uninstall
```
security skill
low Dangerous commands cmd-privilege README.md:78

Privilege escalation / world-writable permissions (documentation of a security skill)
```
sudo bash install.sh
```
security skill
low Dangerous commands cmd-privilege README.md:94

Privilege escalation / world-writable permissions (documentation of a security skill)
```
sudo bash install.sh --uninstall
```
security skill
low Dangerous commands cmd-privilege scripts/check.py:802

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
"  echo 'PermitRootLogin no' | sudo tee /etc/ssh/sshd_config.d/99-n…onf",
```
code literal
low Dangerous commands cmd-privilege scripts/check.py:820

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
"  echo 'PermitRootLogin no' | sudo tee /etc/ssh/sshd_config.d/99-n…onf",
```
code literal
low Dangerous commands cmd-privilege scripts/check.py:868

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
"   echo 'PasswordAuthentication no' | sudo tee /etc/ssh/sshd_config.d/99-n…onf",
```
code literal
low Dangerous commands cmd-privilege scripts/check.py:874

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
"   echo 'PasswordAuthentication no' | sudo tee /etc/ssh/sshd_config.d/99-n…onf",
```
code literal
low Dangerous commands cmd-background-process scripts/check.py:985

Starts a background / autostarted process (string literal in code, not executed)
```
"  sudo systemctl enable fail2ban",
```
code literal
low Dangerous commands cmd-background-process scripts/check.py:993

Starts a background / autostarted process (string literal in code, not executed)
```
"  sudo systemctl enable fail2ban",
```
code literal
low Dangerous commands cmd-privilege scripts/check.py:1107

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
"  sudo cp -r ~/.openclaw /home/openclaw/.openclaw",
```
code literal
low Dangerous commands cmd-background-process scripts/check.py:1391

Starts a background / autostarted process (string literal in code, not executed)
```
"  sudo systemctl enable fail2ban",
```
code literal
low Dangerous commands cmd-background-process scripts/check.py:1397

Starts a background / autostarted process (string literal in code, not executed)
```
"  sudo systemctl enable fail2ban",
```
code literal
low Dangerous commands cmd-cron-mention scripts/check.py:1555

Mentions editing / listing crontab (string literal in code, not executed)
```
("crontab -l 2>/dev/null | grep -i 'backup\\|rsync\\|tar\\|borg\\|restic\\|duplicity'", "cron backup job"),
```
code literal
low Dangerous commands cmd-cron-mention scripts/check.py:1588

Mentions editing / listing crontab (string literal in code, not executed)
```
"  sudo crontab -e",
```
code literal
low Dangerous commands cmd-cron-mention scripts/check.py:1600

Mentions editing / listing crontab (string literal in code, not executed)
```
"  sudo crontab -e",
```
code literal
low Dangerous commands cmd-cron-mention scripts/check.py:1792

Mentions editing / listing crontab (detector / deny-list definition; string literal in code, not executed)
```
("crontab -l 2>/dev/null", "root crontab"),
```
detectorcode literal
low Dangerous commands cmd-cron-mention scripts/check.py:1797

Mentions editing / listing crontab (string literal in code, not executed)
```
stdout, _, code = run_command("crontab -l 2>/dev/null")
```
code literal
low Dangerous commands cmd-background-process scripts/check.py:6144

Starts a background / autostarted process (string literal in code, not executed)
```
"  sudo systemctl enable auditd",
```
code literal

low Dangerous commands cmd-privilege scripts/fix_engine.py:302

Privilege escalation / world-writable permissions (string literal in code, not executed)

"command": "sudo bash -c 'XDG_RUNTIME_DIR=/run/user/0 systemctl --user is-active openclaw-gateway' && sudo bash -c 'XDG_RUNTIME_DIR=/run/user/0 systemctl --user stop openclaw-gateway' && sudo kill $(p

code literal

low Dangerous commands cmd-privilege scripts/fix_engine.py:304

Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)
```
"rollback": "sudo bash -c 'XDG_RUNTIME_DIR=/run/user/0 systemctl --user start openclaw-gateway'",
```
detectorcode literal

low Dangerous commands cmd-privilege scripts/fix_engine.py:313

Privilege escalation / world-writable permissions (string literal in code, not executed; security demo / example)

"command": f"sudo rm -f /root/.config/systemd/user/openclaw-gateway.service && sudo rm -f /root/.config/systemd/user/default.target.wants/openclaw-gateway.service && sudo bash -c 'XDG_RUNTIME_DIR=/run

code literaldemo

low Dangerous commands cmd-privilege scripts/fix_engine.py:315

Privilege escalation / world-writable permissions (string literal in code, not executed; security demo / example)
```
"rollback": f"sudo bash -c 'mkdir -p /root/.config/systemd/user/default.target.wants'",
```
code literaldemo
low Dangerous commands cmd-privilege scripts/fix_engine.py:324

Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)
```
"command": f"mkdir -p {target_openclaw} && sudo bash -c 'cp -r /root/.openclaw/* {target_openclaw}/' && sudo chown -R {target_user}:{target_user} {target_openclaw}",
```
detectorcode literal
low Dangerous commands cmd-disable-security scripts/fix_engine.py:661

Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (detector / deny-list definition; string literal in code, not executed)
```
"rollback": "ufw disable",
```
detectorcode literal
low Dangerous commands cmd-cron-mention scripts/fix_engine.py:720

Mentions editing / listing crontab (string literal in code, not executed)
```
"command": "(crontab -l 2>/dev/null; echo '0 2 * * * ~/.openclaw/backup.sh') | crontab -",
```
code literal
low Dangerous commands cmd-cron-mention scripts/fix_engine.py:721

Mentions editing / listing crontab (string literal in code, not executed)
```
"validation": "crontab -l 2>/dev/null | grep -q backup",
```
code literal
low Dangerous commands cmd-cron-mention scripts/fix_engine.py:722

Mentions editing / listing crontab (detector / deny-list definition; string literal in code, not executed)
```
"rollback": "crontab -l | grep -v backup.sh | crontab -",
```
detectorcode literal
low Dangerous commands cmd-background-process scripts/fix_engine.py:881

Starts a background / autostarted process (string literal in code, not executed)
```
"command": "sudo systemctl enable auditd && sudo systemctl start auditd",
```
code literal
low Dangerous commands cmd-background-process scripts/fix_engine.py:1224

Starts a background / autostarted process (string literal in code, not executed)
```
"command": "sudo systemctl enable openclaw",
```
code literal
low Exfiltration exfil-webhook-url scripts/quarantine_watcher.py:19

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
TELEGRAM_API_URL = f"https://api.telegram.org/bot{BOT_TOKEN}/sendMessage"
```
placeholder
low Exfiltration exfil-webhook-url scripts/skill_scanner.py:350

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
f"https://api.telegram.org/bot{BOT_TOKEN}/sendMessage",
```
placeholder

A further 1 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 60/100

0Result and completion. Does not say what the result is
0Inputs and preconditions. Does not say what the process needs to start
20When it triggers. No condition that starts the skill
30Running it twice. 3 mutating operations with no state check
85Steps. 60 steps, 3 vague phrases
100Tools and files. No external tools needed
100Failures and branches. 2 branches, has a failure section
100Consistency. Name and required fields are in place
100Execution cost. Instruction body is 1673 tokens
100Progress reporting. Reports progress

medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
low 10 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

+5Description has no quoted example phrases that should trigger the skill
+4Description does not say when NOT to use the skill (false activations)
+3Output format is not stated: the model decides each time
-37 of 8 scripts are never mentioned in SKILL.md
+1No license
+2Single-language instructions
+3Description length 193: enough signal without eating the budget
+4Structure: 14 headings
+3Step-by-step instructions: 60 items
+4Has examples (2 code blocks)
+4Reference files are cited in the instructions (1 of 1)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.

Tests

— no evals.json

— no spec.yaml

— not run on models

Files · 17

README.es.md 6K
README.md 5K
SKILL.md 8K
data/skill_blacklist.json 0K
docs/docker-setup-guide.md 8K
extension/openclaw.plugin.json 0K
extension/package.json 0K
install.sh 12K
openclaw.plugin.json 1K
scripts/autoscan.py 5K
scripts/check.py 277K
scripts/cleanup.py 3K
scripts/fix_engine.py 77K
scripts/lgsetup.py 8K
scripts/quarantine_watcher.py 7K
scripts/skill_scanner.py 27K
scripts/telegram_utils.py 2K

Frontmatter

version: 6.1.0

metadata: {"openclaw":{"requires":{"bins":["python3","bash","iptables","auditctl","ss","ufw"],"env":["TELEGRAM_BOT_TOKEN","TELEGRA

Dates

In catalog since —

Updated in catalog 16 Jun 2026

First seen here 7 Sept 2026

Last analysis 11 Sept 2026, 17:43 UTC

Last seen in crawl 2 d ago

Score history

Date		Score	Safety	Qual.
7 Sept 2026	F	29	0	73