SKILLEMALL.ai
GitHub ↗ RU Sign in

BF eeat-openclaw-skill-audit

OpenClaw Skill quality audit based on CORE-EEAT framework adapted for AI agent skills. Evaluates skill's utility (task completion efficiency) and security (safe execution). Features 80 standardized criteria, 8-dimension scoring, veto item detection for security vulnerabilities, and priority improvement recommendations. Applicable for skill selection, security vetting, and skill quality assessment.

ClawHub Agent Skills author: yaoo-2818 v1.0.0 MIT-0 4 files body ≈ 4 140 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 34/100 · Will not run — References files that are not bundled: references/utility-testing-guide.md

AnalyzerInfrastructureAI and agentsSecuritytype 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
B
88/100
safety, quality, tests
Safety 60%
98
Quality 40%
73
Run on models
none yet
Process rating
F
34/100
Will not run
References files that are not bundled: references/utility-testing-guide.md
Tools and files w 18
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.
  2. The text references files that are not there: add them or drop the references.
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-eval-dynamic references/skill-security-checklist.md:47
    Dynamic code execution from decoded/untrusted input (documentation of a security skill)
    os.system(f"curl {user_url}")  # Command injection!
    security skill
  • low Secrets in code secret-password-literal references/skill-security-checklist.md:79
    Hard-coded password / key literal (may be an example) (placeholder value)
    api_key: "sk-p…..."
    placeholder

Files scanned: 4. 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")
  • warning missing-ref reference to a missing file: references/utility-testing-guide.md

Process rating: all ten parameters 34/100

Will not run. References files that are not bundled: references/utility-testing-guide.md
  • 0Tools and files. 1 referenced file(s) missing: references/utility-testing-guide.md
  • 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. 4 mutating operations with no state check
  • 40Consistency. Frontmatter name (eeat-openclaw-skill-audit) differs from the folder (openclaw-skill-eeta-audit)
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 4140 tokens
  • 100Steps. 120 steps
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 12 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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 400: enough signal without eating the budget
  • +4Structure: 45 headings
  • +3Step-by-step instructions: 120 items
  • +3Output format is stated explicitly
  • +4Has examples (9 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.

External checks

ClawHub: clean
This is an instruction-only audit framework for reviewing OpenClaw skills, with scanner hits coming from security-checklist examples rather than active behavior.
LLM: benign (high) · VirusTotal: · 29 May 2026