SKILLEMALL.ai
GitHub ↗ RU Sign in

BC safehub

Scan OpenClaw skills for malware and security issues before installation. Use when the user wants to verify a skill is safe, audit a ClawHub skill, or check a local or GitHub skill.

ClawHub Agent Skills author: sumeetghimire v1.0.2 25 files body ≈ 869 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 63/100 · Has gaps — weak spots: result and completion, running it twice, progress reporting

AnalyzerGitHubDockerData and analyticsSecuritytype 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
89/100
safety, quality, tests
Safety 60%
92
Quality 40%
84
Run on models
none yet
Process rating
C
63/100
Has gaps
Result and completion w 14
0
Progress reporting w 2
0
Running it twice w 4
30
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 · 8

    ✓ No critical or high findings

    Medium and low: 8
    • low Secrets in code secret-high-entropy-token package-lock.json:23
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…dau+gx2EnG7S+uAEe+TWJF…WN4/H8MS…Q6Q==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:60
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…uFK+Hk0Q…Dt7+fGUI…5Hx/ru3azECWTyQ==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:88
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha512-j+gKEx…ahh+s1F2HZ+wAce…RkU++ZWQr…uoQ==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:134
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…rvP+yUUf…4tH/iSSo…tEA==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:152
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…09f+cXft…VU2/9xiCuXMA==",
      detector
    • low Dangerous commands cmd-eval-dynamic rules/obfuscation.yml:32
      Dynamic code execution from decoded/untrusted input (detector / deny-list definition)
      - pattern: eval(atob(...))
      detector
    • low Dangerous commands cmd-eval-dynamic rules/obfuscation.yml:33
      Dynamic code execution from decoded/untrusted input (detector / deny-list definition)
      - pattern: eval(Buffer.from(..., "base64").toString())
      detector
    • low Dangerous commands cmd-eval-dynamic rules/obfuscation.yml:34
      Dynamic code execution from decoded/untrusted input (detector / deny-list definition)
      - pattern: new Function(atob(...))()
      detector

    Files scanned: 25. 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 63/100

    • 0Result and completion. Does not say what the result is
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 2 mutating operations with no state check
    • 55Failures and branches. 1 branches
    • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 8 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 869 tokens
    • low The response is described with custom markup (5 tags): a typed call is more reliable

    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 181: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 8 items
    • +4Has examples (5 code blocks)

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

    External checks

    ClawHub: suspicious
    SafeHub is a legitimate security scanner, but it needs review because crafted GitHub scan targets can reach a shell command and the sandbox report overstates what it actually observes.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026