SKILLEMALL.ai
GitHub ↗ RU Sign in

DC claw-audit

Security scanner and hardening tool for OpenClaw. Use when the user asks about security, wants to scan installed skills for malware or vulnerabilities, audit their OpenClaw configuration, check their security score, or harden their setup. Also triggers on keywords like "scan", "audit", "secure", "vulnerability", "malware", "safe", "hardening", "security score".

Not recommendedlow grade D
modbender/skill-library-mcp Agent Skills author: modbender MIT 31 files · 3 scripts body ≈ 1 254 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Security scanner and hardening tool for OpenClaw.

As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

AnalyzerSecuritytype 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
D
58/100
safety, quality, tests
Safety 60%
39
Quality 40%
86
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

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.

Exfiltration 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 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.

How to improve

    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 · 45

    ✓ No critical or high findings

    Medium and low: 45
    • medium Dangerous commands cmd-pipe-to-shell PROJECT.md:67
      Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)
      | CRIT-001 | Shell execution (curl\|bash, eval, exec) |
      security skill
    • medium Exfiltration exfil-read-secret-files scripts/audit-system-full-async.mjs:991
      Reads credential / secret files (documentation of a security skill)
      const shadow = readFile("/etc/shadow");
      security skill
    • medium Exfiltration exfil-read-secret-files scripts/audit-system.mjs:959
      Reads credential / secret files (documentation of a security skill)
      const shadow = readFile("/etc/shadow");
      security skill
    • medium Dangerous commands cmd-pipe-to-shell SKILL.md:83
      Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)
      - `CRIT-001`: Skill contains shell command execution (curl|bash, eval, exec)
      security skill
    • low Risky intent intent-offensive-security PROJECT.md:69
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | CRIT-003 | Reverse shell (nc -l, /dev/tcp/) |
    • low Dangerous commands cmd-privilege PROJECT.md:313
      Privilege escalation / world-writable permissions (documentation of a security skill)
      sudo tee /etc/sudoers.d/claw-audit << 'EOF'
      security skill
    • low Dangerous commands cmd-privilege PROJECT.md:320
      Privilege escalation / world-writable permissions (documentation of a security skill)
      sudo chmod 440 /etc/sudoers.d/claw-audit
      security skill
    • low Dangerous commands cmd-pipe-to-shell README.md:54
      Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row; documentation of a security skill)
      | CRIT-001 | Shell execution | `curl ... \| bash`, `eval()` |
      tablesecurity skill
    • low Risky intent intent-offensive-security README.md:56
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | CRIT-003 | Reverse shell | `nc -l`, `/dev/tcp/` |
    • low Dangerous commands cmd-pipe-to-shell references/malicious-patterns.json:47
      Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)
      "wget\\s.*&&\\s*(bash|sh|chmod)",
      detectorcode literal
    • low Dangerous commands cmd-privilege scripts/audit-system-async.mjs:130
      Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)
      "Add user to shadow group OR: sudo chmod 644 /etc/ssh/sshd_config");
      code literalsecurity skill
    • low Dangerous commands cmd-background-process scripts/audit-system-async.mjs:345
      Starts a background / autostarted process (string literal in code, not executed; documentation of a security skill)
      "sudo systemctl enable --now fail2ban"
      code literalsecurity skill
    • low Dangerous commands cmd-background-process scripts/audit-system-async.mjs:445
      Starts a background / autostarted process (string literal in code, not executed; documentation of a security skill)
      "sudo systemctl enable --now apt-daily-upgrade.timer"
      code literalsecurity skill
    • low Dangerous commands cmd-privilege scripts/audit-system-full-async.mjs:164
      Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)
      "Add user to shadow group OR: sudo chmod 644 /etc/ssh/sshd_config");
      code literalsecurity skill
    • low Dangerous commands cmd-background-process scripts/audit-system-full-async.mjs:385
      Starts a background / autostarted process (string literal in code, not executed; documentation of a security skill)
      "sudo systemctl enable --now fail2ban"
      code literalsecurity skill
    • low Dangerous commands cmd-background-process scripts/audit-system-full-async.mjs:497
      Starts a background / autostarted process (string literal in code, not executed; documentation of a security skill)
      "sudo systemctl enable --now apt-daily-upgrade.timer"
      code literalsecurity skill
    • low Dangerous commands cmd-background-process scripts/audit-system-full-async.mjs:592
      Starts a background / autostarted process (string literal in code, not executed; documentation of a security skill)
      "sudo apt install apparmor apparmor-utils && sudo systemctl enable --now apparmor"
      code literalsecurity skill
    • low Dangerous commands cmd-privilege scripts/audit-system-full-async.mjs:729
      Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)
      `sudo chmod +t /tmp /var/tmp`
      code literalsecurity skill
    • low Dangerous commands cmd-privilege scripts/audit-system-full-async.mjs:770
      Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)
      `Review each file. Remove SUID bit if not needed: sudo chmod -s <file>`
      code literalsecurity skill
    • low Dangerous commands cmd-privilege scripts/audit-system-full-async.mjs:995
      Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)
      "Add user to shadow group: sudo usermod -aG shadow <user>\n  OR: sudo chmod 640 /etc/shadow && sudo chgrp shadow /etc/shadow");
      code literalsecurity skill
    • low Dangerous commands cmd-background-process scripts/audit-system-full-async.mjs:1078
      Starts a background / autostarted process (string literal in code, not executed; documentation of a security skill)
      "Start logging: sudo systemctl enable --now rsyslog"
      code literalsecurity skill
    • low Dangerous commands cmd-background-process scripts/audit-system-full-async.mjs:1094
      Starts a background / autostarted process (string literal in code, not executed; documentation of a security skill)
      "Install and enable: sudo apt install auditd && sudo systemctl enable --now auditd"
      code literalsecurity skill
    • low Dangerous commands cmd-privilege scripts/audit-system-full-async.mjs:1134
      Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)
      "Fix permissions: sudo chmod 000 /etc/shadow"
      code literalsecurity skill
    • low Dangerous commands cmd-privilege scripts/audit-system.mjs:132
      Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)
      "Add user to shadow group OR: sudo chmod 644 /etc/ssh/sshd_config");
      code literalsecurity skill
    • low Dangerous commands cmd-background-process scripts/audit-system.mjs:353
      Starts a background / autostarted process (string literal in code, not executed; documentation of a security skill)
      "sudo systemctl enable --now fail2ban"
      code literalsecurity skill
    • low Dangerous commands cmd-background-process scripts/audit-system.mjs:465
      Starts a background / autostarted process (string literal in code, not executed; documentation of a security skill)
      "sudo systemctl enable --now apt-daily-upgrade.timer"
      code literalsecurity skill
    • low Dangerous commands cmd-background-process scripts/audit-system.mjs:560
      Starts a background / autostarted process (string literal in code, not executed; documentation of a security skill)
      "sudo apt install apparmor apparmor-utils && sudo systemctl enable --now apparmor"
      code literalsecurity skill
    • low Dangerous commands cmd-privilege scripts/audit-system.mjs:697
      Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)
      `sudo chmod +t /tmp /var/tmp`
      code literalsecurity skill
    • low Dangerous commands cmd-privilege scripts/audit-system.mjs:738
      Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)
      `Review each file. Remove SUID bit if not needed: sudo chmod -s <file>`
      code literalsecurity skill
    • low Dangerous commands cmd-privilege scripts/audit-system.mjs:963
      Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)
      "Add user to shadow group: sudo usermod -aG shadow <user>\n  OR: sudo chmod 640 /etc/shadow && sudo chgrp shadow /etc/shadow");
      code literalsecurity skill
    • low Dangerous commands cmd-background-process scripts/audit-system.mjs:1046
      Starts a background / autostarted process (string literal in code, not executed; documentation of a security skill)
      "Start logging: sudo systemctl enable --now rsyslog"
      code literalsecurity skill
    • low Dangerous commands cmd-background-process scripts/audit-system.mjs:1062
      Starts a background / autostarted process (string literal in code, not executed; documentation of a security skill)
      "Install and enable: sudo apt install auditd && sudo systemctl enable --now auditd"
      code literalsecurity skill
    • low Dangerous commands cmd-privilege scripts/audit-system.mjs:1102
      Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)
      "Fix permissions: sudo chmod 000 /etc/shadow"
      code literalsecurity skill
    • low Risky intent intent-offensive-security SKILL.md:85
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - `CRIT-003`: Skill opens reverse shell or network connections to external hosts
    • low Risky intent intent-offensive-security SKILL.md:111
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      6. **Privilege escalation is refused.** Never run commands that modify sudoers, grant root access, or bypass file permission controls.

    A further 10 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 20. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 51/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 30Running it twice. 6 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 36 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1254 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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

    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • -34 of 10 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 5 example trigger phrases
    • +3Description length 363: enough signal without eating the budget
    • +4Structure: 16 headings
    • +3Step-by-step instructions: 36 items
    • +4Has examples (7 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.