SKILLEMALL.ai
GitHub ↗ RU Sign in

AC mayguard

A security auditor for agent skills. Scans skill directories for malicious patterns (credential theft, suspicious network calls, destructive commands) and provides a safety score. Use before installing unknown skills.

modbender/skill-library-mcp Agent Skills author: modbender MIT 3 files body ≈ 456 tokens Open the sourcegithub.com↗ analyzed 2 d ago

A security auditor for agent skills.

As a process C 59/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerData and analyticsAI 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
94/100
safety, quality, tests
Safety 60%
98
Quality 40%
87
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • low Dangerous commands cmd-privilege references/threat_patterns.json:24
      Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)
      "chmod 777",
      code literalsecurity skill
    • low Risky intent intent-offensive-security SKILL.md:39
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - **Destructive Commands:** `rm -rf /`, disk formatting, or privilege escalation.

    Files scanned: 3. 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 59/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 55Failures and branches. 1 branches
    • 100Tools and files. No external tools needed
    • 100Steps. 10 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 456 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
    • +1No license
    • +2Single-language instructions
    • +3Description length 217: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 10 items
    • +4Has examples (2 code blocks)
    • +3All 1 scripts are documented

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