SKILLEMALL.ai
GitHub ↗ RU Sign in

AC skill-guard

Audit a skill package for malicious, poisoned, or deceptive content before installation or activation. Use when the user asks to install, activate, or load a skill from any external or untrusted source — including .skill files, cloned directories, or skills sent by other users. Detects prompt injection, malicious scripts, deceptive descriptions, and hidden instructions.

ClawHub Agent Skills author: 王昊宇 v1.0.0 MIT-0 2 files body ≈ 977 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 53/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, consistency

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
93/100
safety, quality, tests
Safety 60%
97
Quality 40%
87
Run on models
none yet
Process rating
C
53/100
Has gaps
Inputs and preconditions w 11
0
Failures and branches w 10
0
Progress reporting w 2
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 · 3

    ✓ No critical or high findings

    Medium and low: 3
    • low Risky intent intent-offensive-security SKILL.md:94
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      | Malicious script | scripts/ | Reverse shell, data exfiltration, persistence mechanism |
      detector

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

    Files scanned: 2. 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 53/100

    • 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
    • 30Running it twice. 1 mutating operations with no state check
    • 40Consistency. Frontmatter name (skill-guard) differs from the folder (haoyuwang99-skill-guard)
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 16 steps
    • 100Execution cost. Instruction body is 977 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)
    • +1No license
    • +2Single-language instructions
    • +3Description length 372: enough signal without eating the budget
    • +4Structure: 11 headings
    • +3Step-by-step instructions: 16 items
    • +3Output format is stated explicitly
    • +4Has examples (2 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.

    External checks

    ClawHub: clean
    This skill is a security-review checklist for auditing other skills, and the risky phrases it contains are examples of what to detect rather than commands to follow.
    LLM: benign (high) · VirusTotal: · 29 May 2026