SKILLEMALL.ai
GitHub ↗ RU Sign in

BC clawd-zero-trust

Zero Trust security hardening for OpenClaw deployments. Use when asked to audit, harden, or apply Zero Trust architecture to an OpenClaw instance — including NHI identity scoping, Principle of Least Privilege (PLP), Plan-First protocol, DNS-based egress filtering, plugin allowlisting, and SSH/network lockdown. Also triggers on security audit requests, vulnerability analysis, SecureClaw installation, firewall hardening, and post-deployment security reviews.

modbender/skill-library-mcp Agent Skills author: modbender MIT 22 files · 7 scripts body ≈ 2 118 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Zero Trust security hardening for OpenClaw deployments.

As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

ProcedureTelegramAI and agentsSecuritytype 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
88/100
safety, quality, tests
Safety 60%
93
Quality 40%
80
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
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 · 3

    ✓ No critical or high findings

    Medium and low: 3
    • medium Dangerous commands cmd-privilege scripts/whitelist.sh:29
      Privilege escalation / world-writable permissions
      sudo bash "$FILTER_SCRIPT" --apply --force
    • low Risky intent intent-offensive-security references/false-positives.md:16
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - `[env-harvesting]` Credential harvesting patterns
    • low Risky intent intent-offensive-security SECURITY.md:38
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - `harden.sh` — config mutation, privilege escalation vectors

    Files scanned: 22. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"

    Process rating: all ten parameters 56/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 1 mutating operations with no state check
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 21 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2118 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

    • +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
    • -31 of 9 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 460: enough signal without eating the budget
    • +4Structure: 19 headings
    • +3Step-by-step instructions: 21 items
    • +4Has examples (11 code blocks)
    • +4Reference files are cited in the instructions (2 of 2)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.