SKILLEMALL.ai
GitHub ↗ RU Sign in

CC reefwatch

Continuous local security monitoring daemon for Linux and macOS. Detects brute-force attacks, malware, privilege escalation, suspicious processes, file tampering, cryptominers, and network anomalies using YARA, Sigma, and custom detection rules. Runs as a background process and alerts only when real threats are found. Use when the user wants host-level intrusion detection, security monitoring, threat scanning, or asks about suspicious activity on their machine.

modbender/skill-library-mcp Agent Skills author: modbender MIT 41 files body ≈ 940 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Continuous local security monitoring daemon for Linux and macOS.

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

ProcedureInfrastructuretype 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
C
67/100
safety, quality, tests
Safety 60%
57
Quality 40%
82
Run on models
none yet
Process rating
C
60/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
55
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.

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 · 19

    ✓ No critical or high findings

    Medium and low: 19
    • medium Dangerous commands cmd-persistence README.md:85
      Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
      cp service/com.reefwatch.daemon.plist ~/Library/LaunchAgents/
      security skill
    • medium Dangerous commands cmd-persistence README.md:86
      Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
      launchctl load ~/Library/LaunchAgents/com.reefwatch.daemon.plist
      security skill
    • medium Dangerous commands cmd-persistence reefwatch_config.yaml:58
      Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
      - "/etc/crontab"
      code literal
    • medium Dangerous commands cmd-persistence reefwatch_config.yaml:65
      Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
      - "~/Library/LaunchAgents/"
      code literal
    • medium Dangerous commands cmd-persistence reefwatch_config.yaml:66
      Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
      - "/Library/LaunchDaemons/"
      code literal
    • medium Dangerous commands cmd-persistence reefwatch/daemon.py:89
      Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
      "/etc/crontab",
      code literal
    • low Risky intent intent-offensive-security README.md:14
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      - **Malware** -- Known signatures via YARA (webshells, miners, ransomware, RATs)
      detector
    • low Risky intent intent-offensive-security README.md:15
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - **Privilege escalation** -- SUID abuse, sudo exploits, unauthorized root access
    • low Secrets in code secret-high-entropy-token reefwatch/engines/custom_rules.py:39
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "ZGlz…mcp",
      quoted
    • low Secrets in code secret-high-entropy-token reefwatch/engines/custom_rules.py:40
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "bmV3…XB0",
      quoted
    • low Secrets in code secret-high-entropy-token reefwatch/engines/custom_rules.py:43
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "c3Vi…W4p",
      quoted
    • low Secrets in code secret-high-entropy-token reefwatch/engines/custom_rules.py:46
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "YWN0…W91",
      quoted
    • low Dangerous commands cmd-eval-dynamic setup_rules.py:384
      Dynamic code execution from decoded/untrusted input (quoted — discussed, not commanded)
      $py1 = "exec(compile(" ascii
      quoted
    • low Dangerous commands cmd-privilege setup_rules.py:445
      Privilege escalation / world-writable permissions (string literal in code, not executed)
      $s5 = "chmod 777" ascii
      code literal
    • low Risky intent intent-offensive-security SKILL.md:4
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      description: "Continuous local security monitoring daemon for Linux and macOS. Detects brute-force attacks, malware, privilege escalation, suspicious processes, file tampering, cryptominers, and netwo
      detector
    • low Risky intent intent-offensive-security SKILL.md:26
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      - **YARA**: File and process scanning for malware, webshells, miners, ransomware
      detector
    • low Risky intent intent-offensive-security SKILL.md:27
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      - **Sigma**: Log-based detection for brute-force, privilege escalation, lateral movement
      detector
    • low Risky intent intent-offensive-security threat_catalog.md:19
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Ransomware indicators | YARA | CRITICAL | Ransom note patterns, encryption behaviors |
    • low Risky intent intent-offensive-security threat_catalog.md:22
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ### Privilege Escalation

    Files scanned: 26. 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 60/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 55Failures and branches. 1 branches
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 12 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 940 tokens
    • 100Running it twice. No mutating operations
    • 100Progress reporting. Reports progress

    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
    • -2localhost URLs: will not work for another user
    • +1No license
    • +2Single-language instructions
    • +3Description length 465: enough signal without eating the budget
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 12 items
    • +4Has examples (10 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.