SKILLEMALL.ai

AC skillguard

Security scanner for OpenClaw/ClawHub skills. Detects malware, reverse shells, credential theft, prompt injection, memory poisoning, typosquatting, and suspicious prerequisites before installation. Use when installing new skills, auditing existing skills, checking a skill name for typosquatting, or scanning ClawHub skills for security risks.

modbender/skill-library-mcp Agent Skills author: modbender MIT 4 files body ≈ 752 tokens Open the sourcegithub.com analyzed 2 d ago

Security scanner for OpenClaw/ClawHub skills.

As a process C 57/100 · Has gaps — weak spots: when it triggers, failures and branches, consistency

AnalyzerSecurityAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
93/100
safety, quality, tests
Safety 60%
92
Quality 40%
94
Run on models
none yet
Process rating
C
57/100
Has gaps
Failures and branches w 10
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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 · 4

    ✓ No critical or high findings

    Medium and low: 4
    • low Risky intent intent-offensive-security references/threat-landscape.md:26
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - No bug bounty program, no dedicated security team at OpenClaw
    • low Risky intent intent-offensive-security references/threat-landscape.md:38
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ### Reverse Shell Backdoor
    • low Risky intent intent-offensive-security references/threat-landscape.md:39
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      Hidden in functional code — skill works normally but also opens a reverse shell.

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

    Files scanned: 4. 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 57/100

    • 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
    • 40Consistency. Frontmatter name (skillguard) differs from the folder (skillguard-scanner)
    • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 25 steps
    • 100Execution cost. Instruction body is 752 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)
    • +1No license
    • +2Single-language instructions
    • +3Description length 343: enough signal without eating the budget
    • +4Structure: 17 headings
    • +3Step-by-step instructions: 25 items
    • +3Output format is stated explicitly
    • +4Has examples (4 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.