SKILLEMALL.ai
GitHub ↗ RU Sign in

AF openclaw-sacred-rules

OpenClaw configuration safety rules to prevent system disasters. Use when: (1) Making OpenClaw config changes, (2) Troubleshooting auth failures, (3) Taking system backups, (4) Recovering from config disasters, (5) User asks about config best practices, or (6) Before enabling/disabling system features like sandbox mode.

modbender/skill-library-mcp Agent Skills author: modbender MIT 6 files · 3 scripts body ≈ 536 tokens Open the sourcegithub.com↗ analyzed 2 d ago

OpenClaw configuration safety rules to prevent system disasters.

As a process F 31/100 · Will not run — weak spots: steps, result and completion, when it triggers

GeneratorAI and agentstype 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
A
90/100
safety, quality, tests
Safety 60%
91
Quality 40%
88
Run on models
none yet
Process rating
F
31/100
Will not run
Steps w 15
0
Result and completion w 14
0
Inputs and preconditions w 11
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.

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 · 5

    ✓ No critical or high findings

    Medium and low: 5
    • medium Dangerous commands cmd-persistence scripts/safe_backup.sh:26
      Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
      "$HOME/Library/LaunchAgents/ai.openclaw.gateway.plist"
      code literal
    • low Exfiltration read-dotenv references/recovery.md:109
      Reads a .env file (documentation of a security skill)
      source ~/.openclaw/.env && openclaw auth <command>
      security skill
    • low Exfiltration read-dotenv references/recovery.md:130
      Reads a .env file (documentation of a security skill)
      source ~/.openclaw/.env && openclaw auth regenerate
      security skill
    • low Exfiltration read-dotenv scripts/auth_checker.sh:76
      Reads a .env file (detector / deny-list definition)
      echo "   3. Try: source ~/.openclaw/.env && openclaw auth <provider>"
      detector
    • low Exfiltration read-dotenv SKILL.md:39
      Reads a .env file (documentation of a security skill)
      source ~/.openclaw/.env && openclaw auth <command>
      security skill

    Files scanned: 6. 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 31/100

    • 0Steps. Prose only: no discrete steps
    • 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
    • 60Tools and files. Uses tools (read) that frontmatter does not declare
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 536 tokens
    • 100Running it twice. No mutating operations
    • 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)
    • +3No numbered steps or checklist
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 321: enough signal without eating the budget
    • +4Structure: 15 headings
    • +4Has examples (6 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)
    • +3All 4 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.