SKILLEMALL.ai
GitHub ↗ RU Sign in

BD openclaw-shield

OpenClaw cloud security guardrail that enforces pre-execution checks, source trust classification, taint tracking, metadata endpoint blocking, and output redaction. Use when Codex is asked to run shell commands, read or write files, make network requests, install packages, or design and review Shield policies for cloud-server deployments.

ClawHub Agent Skills author: Eilaiwangwh v1.0.0 MIT-0 8 files body ≈ 448 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 39/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerInfrastructuretype 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
89/100
safety, quality, tests
Safety 60%
93
Quality 40%
84
Run on models
none yet
Process rating
D
39/100
Unfinished process
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.

Instruction override 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 text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

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 Instruction override en-ignore-previous references/detection-and-redaction.md:7
      Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)
      - 指令覆盖: ignore previous instructions, forget above
      security skill

    A further 2 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 8. 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 39/100

    • 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
    • 40Consistency. Frontmatter name (openclaw-shield) differs from the folder (openclaw-shield-v1)
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 100Steps. 44 steps
    • 100Execution cost. Instruction body is 448 tokens

    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
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +3Description length 340: enough signal without eating the budget
    • +4Structure: 7 headings
    • +3Step-by-step instructions: 44 items
    • +4Reference files are cited in the instructions (4 of 4)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

    External checks

    ClawHub: suspicious
    This is a security guardrail skill, but its own instructions make the guardrail easy to bypass and rely on a missing or mismatched runtime checker.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026