SKILLEMALL.ai
RU Sign in

BC castreader

Read any web page aloud with natural AI voices. Extract article text from any URL and convert it to audio (MP3). Use when the user wants to: listen to a webpage, read an article aloud, convert URL to audio, text-to-speech for a link, read this page to me, listen to this article.

ClawHub Agent Skills author: vinxu v2.1.1 MIT-0 12 files body ≈ 582 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

GeneratorWriting and documentstype 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
78/100
safety, quality, tests
Safety 60%
79
Quality 40%
77
Run on models
none yet
Process rating
C
55/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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 · 9

    ✓ No critical or high findings

    Medium and low: 9
    • medium Exfiltration net-redirectable-api-key scripts/generate-paragraph.js:25
      Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
      API key + configurable base URL from environment
    • medium Exfiltration net-redirectable-api-key scripts/generate-text.js:16
      Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
      API key + configurable base URL from environment
    • medium Exfiltration net-redirectable-api-key scripts/read-url.js:29
      Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
      API key + configurable base URL from environment
    • low Secrets in code secret-high-entropy-token package-lock.json:78
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…bKX+KS9G…yMA/NhKJ…RGz/Q==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:139
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…Wwy+ghLE…vfU/YnxW…fdg==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:260
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…2BV+FY5ZFezP/ypmwayk68+NzzA…NFD/uUmBJuGoXw==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:302
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…vZS+VIDU…jX4+qx9M…saQ==",
      detector
    • low Secrets in code secret-high-entropy-token package-lock.json:391
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…GLw+xYSd…cqA==",
      detector
    • low Dangerous commands cmd-privilege scripts/extract.js:33
      Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)
      args: ['--no-sandbox', '--disable-setuid-sandbox'],
      detectorcode literal

    Files scanned: 12. 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 55/100

    • 0Result and completion. Does not say what the result is
    • 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. 4 mutating operations with no state check
    • 40Consistency. Frontmatter name (castreader) differs from the folder (castreader-openclaw-skill)
    • 100Tools and files. No external tools needed
    • 100Steps. 4 steps
    • 100When it triggers. States when to use and when not to
    • 100Execution cost. Instruction body is 582 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
    • -41 reference files, but SKILL.md never points to them: the model will not open them
    • -34 of 6 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 279: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 4 items
    • +4Has examples (7 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.

    External checks

    ClawHub: suspicious
    CastReader does what it claims, but it can extract sensitive page content and send it to remote services over an insecure default connection.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026