SKILLEMALL.ai

BD skill-auditor

The definitive security scanner for OpenClaw skills. 18 security checks including prompt injection detection, download-and-execute, privilege escalation, credential harvesting, supply chain attacks, crypto drains, and more. 5-dimension trust scoring with trend tracking.

modbender/skill-library-mcp Agent Skills author: modbender MIT 14 files · 8 scripts body ≈ 1 597 tokens Open the sourcegithub.com analyzed 2 d ago

The definitive security scanner for OpenClaw skills.

As a process D 39/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerSoftware developmentData and analyticsAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
79/100
safety, quality, tests
Safety 60%
84
Quality 40%
72
Run on models
none yet
Process rating
D
39/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 16

✓ No critical or high findings

Medium and low: 16
  • low Risky intent intent-offensive-security CHANGELOG.md:24
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **Check 18: Privilege Escalation** (CRITICAL) - Detects sudo commands, chmod 777/setuid, writes to system paths (/usr/local/bin, /etc/), chown root.
  • low Risky intent intent-offensive-security CHANGELOG.md:97
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Credential harvesting detection
  • low Risky intent intent-offensive-security SKILL.md:4
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    description: "The definitive security scanner for OpenClaw skills. 18 security checks including prompt injection detection, download-and-execute, privilege escalation, credential harvesting, supply ch
    detector
  • low Risky intent intent-offensive-security SKILL.md:150
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    Malicious fixtures: credential harvest, obfuscated payload, sensitive fs reads, crypto wallets, time bombs, symlink attacks, prompt injection, download-execute, privilege escalation.
    detector
  • low Risky intent intent-offensive-security TEST-FIXTURES-WARNING.md:13
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition; test fixture / example file)
    | malicious-basic | Credential harvesting + network exfiltration |
    detectorfixture

A further 11 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 39/100

  • 0Result and completion. Does not say what the result is
  • 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
  • 40Consistency. Frontmatter name (skill-auditor) differs from the folder (yoder-skill-auditor)
  • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
  • 85Steps. 20 steps, 1 vague phrases
  • 100Execution cost. Instruction body is 1597 tokens
  • 100Running it twice. No mutating operations
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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 270: enough signal without eating the budget
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 20 items
  • +4Has examples (4 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.