SKILLEMALL.ai
GitHub ↗ RU Sign in

AC clawshield

OpenClaw security audit + prompt injection detector. Scans gateway/vulns/cron/PI patterns. Use for frenzy-proofing installs.

ClawHub Agent Skills author: Poolguy24 v1.1.0 5 files · 1 script body ≈ 309 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerAI and agentsInfrastructuretype 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%
98
Quality 40%
78
Run on models
none yet
Process rating
C
53/100
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

    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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • low Risky intent intent-offensive-security references/threats.md:11
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - **Privilege escalation / secret hunting** (requests for system prompts, API keys, or environment secrets)
    • low Risky intent intent-offensive-security references/threats.md:12
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      - **Unauthorized network discovery** (port scans, lateral movement beyond localhost)
      detector

    Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "display_name"
    • note frontmatter-key unknown frontmatter key "price"
    • note frontmatter-key unknown frontmatter key "inputs"
    • note frontmatter-key unknown frontmatter key "outputs"

    Process rating: all ten parameters 53/100

    • 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
    • 100Tools and files. No external tools needed
    • 100Steps. 9 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 309 tokens
    • 100Running it twice. No mutating operations

    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
    • -41 reference files, but SKILL.md never points to them: the model will not open them
    • +1No license
    • +2Single-language instructions
    • +3Description length 124: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 9 items
    • +4Has examples (3 code blocks)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.

    External checks

    ClawHub: clean
    ClawShield is a local security-audit skill that stays on the machine, but its reports can include sensitive local snippets and its documentation advertises some missing helper features.
    LLM: benign (high) · VirusTotal: benign · 28 May 2026