SKILLEMALL.ai
GitHub ↗ RU Sign in

BB repo-analyzer

GitHub repository trust scoring and due diligence. Use when asked to analyze, audit, score, or evaluate any GitHub repo — especially for crypto/DeFi project DD, checking if a repo is legit, evaluating code quality, verifying team credibility, or comparing multiple repos. Also handles X/Twitter URLs containing GitHub links — auto-extracts and analyzes repos from tweets. Triggers on "analyze this repo", "is this legit", "check this GitHub", "trust score", "audit this project", "repo quality", "batch scan repos", "analyze this tweet". ALSO auto-triggers when the user pastes an X/Twitter URL that contains a GitHub link — no explicit "analyze" command needed. When triggered by a tweet, ALWAYS include the tweet text/context above the analysis. Do NOT use for general GitHub browsing, reading READMEs, or cloning repos without analysis.

modbender/skill-library-mcp Agent Skills author: modbender MIT 7 files body ≈ 1 016 tokens Open the sourcegithub.com↗ analyzed 3 d ago

GitHub repository trust scoring and due diligence.

As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, failures and branches, running it twice

AnalyzerGitHubSoftware developmentWriting and documentsData and analyticstype 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
86/100
safety, quality, tests
Safety 60%
83
Quality 40%
90
Run on models
none yet
Process rating
B
66/100
Nearly there
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

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 · 5

    ✓ No critical or high findings

    Medium and low: 5
    • medium Dangerous commands cmd-pipe-to-shell scripts/analyze.js:1723
      Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
      warnings.push(`${fileName} uses curl|sh install from own domain: "${m[0].trim().substring(0, 80)}" — standard but runs unaudited code`);
      code literal
    • medium Dangerous commands cmd-pipe-to-shell scripts/analyze.js:1725
      Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
      criticals.push(`${fileName} uses curl|sh install from unknown URL: "${m[0].trim().substring(0, 80)}" — executes unaudited remote code`);
      code literal
    • medium Dangerous commands cmd-pipe-to-shell scripts/analyze.js:1993
      Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
      agentSafety.critical.push('SKILL.md uses curl|bash install pattern — executes unaudited remote code');
      code literal
    • low Dangerous commands cmd-privilege scripts/analyze.js:1988
      Privilege escalation / world-writable permissions (string literal in code, not executed)
      if (/\bsudo\b|as root|chmod 777|--privileged/i.test(skillContent)) {
      code literal
    • low Risky intent intent-offensive-security SKILL.md:83
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      - **Agent safety**: Detects prompt injection, credential harvesting, install script hooks, obfuscated code
      detector

    Files scanned: 7. 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 66/100

    • 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
    • 30Running it twice. 6 mutating operations with no state check
    • 60Result and completion. Output format stated, no completion criterion
    • 85Steps. 21 steps, 1 vague phrases
    • 100Tools and files. Tools declared in frontmatter
    • 100When it triggers. States when to use and when not to
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1016 tokens

    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

    • +3Description length 839: 120–800 characters recommended
    • -32 of 3 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 9 example trigger phrases
    • +4Description says when NOT to use the skill
    • +4Structure: 10 headings
    • +3Step-by-step instructions: 21 items
    • +3Output format is stated explicitly
    • +4Has examples (2 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.