SKILLEMALL.ai
GitHub ↗ RU Sign in

BC captcha-relay

Human-in-the-loop CAPTCHA solving with two modes: screenshot (default, zero infrastructure) and token relay (requires network access). Screenshot mode captures the page with a grid overlay, sends it to the human, and injects clicks based on their reply. Token relay mode detects CAPTCHA type + sitekey, serves the real widget on a relay page for native solving, and injects the token via CDP.

ClawHub Agent Skills author: 0xclanky v2.1.0 20 files body ≈ 803 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches

AnalyzerInfrastructuretype 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
87/100
safety, quality, tests
Safety 60%
90
Quality 40%
83
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
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 · 6

    ✓ No critical or high findings

    Medium and low: 6
    • medium Dangerous commands cmd-pipe-to-shell-known-host TAILSCALE.md:19
      Pipe-to-shell installer from a well-known host (still executes remote code)
      curl -fsSL https://tailscale.com/install.sh | sh
    • low Secrets in code secret-high-entropy-token package-lock.json:200
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…xgu+qFKS…BMQ==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:244
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha512-y/5PCd+mP4CA/sPDKl2961b+C9d+vPAv…CuH+1kW8…a4Q==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:389
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…ykh+CeBd…VHy+moaqkpL/jqQq…W4A==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:420
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…oDP+fZsw/ZerEMsW/pyzsRbElpsL/DBVW…5Eg==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:445
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…8CM+MzKM…4lA==",
      detector

    Files scanned: 20. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "defaultMode"

    Process rating: all ten parameters 51/100

    • 0Result and completion. Does not say what the result is
    • 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. 3 mutating operations with no state check
    • 60Tools and files. Uses tools (node) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 17 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 803 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

    • +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 392: enough signal without eating the budget
    • +4Structure: 10 headings
    • +3Step-by-step instructions: 17 items
    • +4Has examples (4 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

    External checks

    ClawHub: suspicious
    This skill openly helps relay and inject CAPTCHA solutions, but it exposes browser/session data and control through unauthenticated network-facing relays.
    LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026