SKILLEMALL.ai
RU Sign in

AC capsolver

Use capsolver to automatically resolve Geetest, reCAPTCHA v2, reCAPTCHA v3, MTCaptcha, DataDome, AWS WAF, Cloudflare Turnstile, and Cloudflare Challenge, etc.

ClawHub Agent Skills author: capsolver v1.0.1 MIT-0 5 files body ≈ 3 840 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 60/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, consistency

ProcedureAWSCloudflareInfrastructuretype 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
A
90/100
safety, quality, tests
Safety 60%
92
Quality 40%
87
Run on models
none yet
Process rating
C
60/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
20
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 Exfiltration read-dotenv README.md:78
      Reads a .env file
      cp .env.example .env
    • low Secrets in code secret-high-entropy-token scripts/solver.py:34
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      'ReCa…ess',
      quoted
    • low Secrets in code secret-high-entropy-token scripts/solver.py:38
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      'ReCa…ess',
      quoted
    • low Secrets in code secret-high-entropy-token scripts/solver.py:380
      High-entropy token-like string (may be an id, hash or a credential)
      # ReCa…ess
    • low Secrets in code secret-high-entropy-token scripts/solver.py:381
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      pars…ist = ['ReCa…ess', 'ReCa…ask', 'ReCa…ess']
      quoted
    • low Secrets in code secret-high-entropy-token scripts/solver.py:395
      High-entropy token-like string (may be an id, hash or a credential)
      # ReCa…ess
    • low Obfuscation obf-base64-blob SKILL.md:461
      Long base64-looking blob (quoted — discussed, not commanded)
      "cookie": "223d…wt9+Butf…XFl
      quoted
    • low Obfuscation obf-base64-blob SKILL.md:476
      Long base64-looking blob (quoted — discussed, not commanded)
      "token": "0.mF…ift
      quoted

    Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"
    • note frontmatter-key unknown frontmatter key "credentials"
    • note frontmatter-key unknown frontmatter key "env"

    Process rating: all ten parameters 60/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 40Consistency. Frontmatter name (capsolver) differs from the folder (capsolver-captcha-solver)
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 100Steps. 70 steps
    • 100Failures and branches. 5 branches, has a failure section
    • 100Execution cost. Instruction body is 3840 tokens
    • 100Running it twice. No mutating operations

    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 158: enough signal without eating the budget
    • +4Structure: 28 headings
    • +3Step-by-step instructions: 70 items
    • +3Output format is stated explicitly
    • +4Has examples (26 code blocks)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.

    External checks

    ClawHub: suspicious
    This skill is transparent about using CapSolver, but it gives broad CAPTCHA and anti-bot bypass capability while sending sensitive challenge, proxy, and page data to a third party.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026