SKILLEMALL.ai

BC skill-shield

Security audit tool for ClawHub skills. Scans a skill directory with 65 detection patterns, anti-obfuscation analysis, and dual rating system (Security + Compliance). v0.6.1 fixes batch scan performance by skipping venv/node_modules directories. Use when: installing a new skill, reviewing skill safety, or auditing permissions.

modbender/skill-library-mcp Agent Skills author: modbender MIT 5 files body ≈ 1 736 tokens Open the sourcegithub.com analyzed 2 d ago

Security audit tool for ClawHub skills.

As a process C 52/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches

AnalyzerGitHubSoftware developmentSecuritytype and topics are labelled automatically from the skill text
JSON
Technical rating
B
87/100
safety, quality, tests
Safety 60%
89
Quality 40%
84
Run on models
none yet
Process rating
C
52/100
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 · 11

    ✓ No critical or high findings

    Medium and low: 11
    • low Dangerous commands cmd-privilege scripts/scan.py:115
      Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)
      ("setuid",         "setuid/setgid",         r"\b(setuid|setgid|seteuid)\b",        5, "privilege_escalation", "CWE-269"),
      code literalsecurity skill
    • low Dangerous commands cmd-privilege scripts/scan.py:444
      Privilege escalation / world-writable permissions (string literal in code, not executed; code comment; documentation of a security skill)
      # --- v0.3.0 FIX: setuid in --disable-setuid-sandbox is a browser flag, not privilege escalation ---
      code literalcommentsecurity skill
    • low Risky intent intent-offensive-security SKILL.md:53
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Network exfiltration: curl POST, wget --post, requests.post, fetch POST, netcat reverse shell, DNS exfil, pipe to curl, socat (9 patterns)
    • low Dangerous commands cmd-privilege SKILL.md:56
      Privilege escalation / world-writable permissions (documentation of a security skill)
      - Privilege escalation: sudo, su, chmod 777, chown, setuid/setgid, doas (6 patterns)
      security skill
    • low Risky intent intent-offensive-security SKILL.md:56
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Privilege escalation: sudo, su, chmod 777, chown, setuid/setgid, doas (6 patterns)
    • low Secrets in code secret-high-entropy-token SKILL.md:172
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      Tips welcome: `0x6c…806` (Base)
      quoted

    A further 5 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 5. 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 52/100

    • 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
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 1 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 100Steps. 48 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1736 tokens
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 10 top-level sections: this looks like several domains in one skill

    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)
    • -31 of 2 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 328: enough signal without eating the budget
    • +4Structure: 30 headings
    • +3Step-by-step instructions: 48 items
    • +3Output format is stated explicitly
    • +4Has examples (5 code blocks)

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