SKILLEMALL.ai
RU Sign in

AC skill-audit

Runs a deterministic static safety audit for third-party AI skill or plugin repositories before install or execution. Use when asked to scan a skill repo, assess whether a repo is safe to install, run a skill safety assessment, or produce evidence-backed findings for pre-install security screening.

ClawHub Agent Skills author: modeioai v0.1.0 MIT-0 37 files body ≈ 844 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 54/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches

AnalyzerGitHubInfrastructuretype 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
95/100
safety, quality, tests
Safety 60%
97
Quality 40%
91
Run on models
none yet
Process rating
C
54/100
Has gaps
Result and completion w 14
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 references/prompt-contract.md:33
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Likely exploit chain
    • low Risky intent intent-offensive-security SKILL.md:29
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - prompt payload generation through `prompt`

    A further 1 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 34. 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 54/100

    • 0Result and completion. Does not say what the result is
    • 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. 2 mutating operations with no state check
    • 40Consistency. Frontmatter name (skill-audit) differs from the folder (skill-audit-modeio)
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Tools and files. No external tools needed
    • 100Steps. 23 steps
    • 100Execution cost. Instruction body is 844 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
    • +1No license
    • +2Single-language instructions
    • +3Description length 299: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 23 items
    • +4Has examples (3 code blocks)
    • +4Reference files are cited in the instructions (3 of 4)
    • +3All 2 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.

    External checks

    ClawHub: clean
    This is a repository-audit tool whose file reading, GitHub checks, and optional GitHub token use fit its stated security-review purpose, though users should notice the default network precheck.
    LLM: benign (high) · VirusTotal: · 29 May 2026