SKILLEMALL.ai
GitHub ↗ RU Sign in

BC safe-guardian

A safe security layer plugin for OpenClaw that intercepts dangerous tool calls (exec, write, edit) through multi-layer blacklist/whitelist filtering and intent validation with comprehensive audit logs.

ClawHub Agent Skills author: kvs-GoN v1.1.1 MIT-0 7 files body ≈ 2 218 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

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

AnalyzerSecurityInfrastructuretype 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
B
83/100
safety, quality, tests
Safety 60%
94
Quality 40%
66
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

How to improve

  1. 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 · 6

✓ No critical or high findings

Medium and low: 6
  • low Dangerous commands cmd-privilege config/blacklist.json:32
    Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)
    "chmod 777",
    code literalsecurity skill
  • low Dangerous commands cmd-privilege index.js:107
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    'chmod 777',
    code literal
  • low Dangerous commands cmd-disable-security index.js:116
    Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (detector / deny-list definition; string literal in code, not executed)
    'iptables -F',
    detectorcode literal
  • low Dangerous commands cmd-destructive-fs-scoped test.js:26
    Destructive command on a partition / current directory (normal in admin docs; verify the target) (detector / deny-list definition; string literal in code, not executed; test fixture / example file)
    const dang…ll2 = 'dd if=/dev/zero of=/dev/sda';
    detectorcode literalfixture
  • low Dangerous commands cmd-destructive-fs-scoped test.js:34
    Destructive command on a partition / current directory (normal in admin docs; verify the target) (detector / deny-list definition; string literal in code, not executed; test fixture / example file)
    const dang…ll3 = 'mkfs.ext4 /dev/sda1';
    detectorcode literalfixture

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

Files scanned: 7. 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 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
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 1 mutating operations with no state check
  • 100Tools and files. No external tools needed
  • 100Steps. 31 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2218 tokens
  • low 16 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
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -229 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 201: enough signal without eating the budget
  • +4Structure: 51 headings
  • +3Step-by-step instructions: 31 items
  • +4Has examples (24 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.

External checks

ClawHub: suspicious
This appears to be a security guard/audit skill, but the reported allowlist and plaintext logging create sensitive local-data exposure risks that need review before install.
LLM: suspicious (medium) · VirusTotal: · 29 May 2026