SKILLEMALL.ai
GitHub ↗ RU Sign in

CD reach

Agent web interface. Browse websites, fill forms, login to services, sign transactions, send/receive email, solve CAPTCHAs, and interact with the web autonomously.

ClawHub Agent Skills author: Potdealer v0.2.0 MIT-0 35 files body ≈ 1 011 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process D 48/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationAI and agentsInfrastructuretype 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
C
70/100
safety, quality, tests
Safety 60%
68
Quality 40%
72
Run on models
none yet
Process rating
D
48/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
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.

Risky intent 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 purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.

For the author

Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.

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

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 16

✓ No critical or high findings

Medium and low: 16
  • medium Risky intent intent-wallet-secrets README.md:537
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    | `PRIVATE_KEY` | For sign/pay | Ethereum wallet private key |
  • medium Risky intent intent-wallet-secrets SKILL.md:114
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    PRIVATE_KEY=0x...           # Wallet private key for signing/payments
  • medium Exfiltration net-redirectable-api-key src/primitives/email.js:437
    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 intent-browser-credential-store src/utils/cookie-import.js:212
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    === Export Cookies from Chrome/Edge ===
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:39
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…jgR+Mkmf+D189…ihQ==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:150
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…uWm+fFRcIOgKBMiOBP+eXiy…9ab+DDKA==",
    detector
  • low Exfiltration read-dotenv README.md:14
    Reads a .env file
    cp .env.example .env  # Add your keys
  • low Dangerous commands cmd-privilege src/browser.js:30
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    '--disable-setuid-sandbox',
    code literal
  • low Secrets in code secret-high-entropy-token src/primitives/pay.js:15
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    USDC: '0x83…913',
    quoted
  • low Secrets in code secret-high-entropy-token src/primitives/pay.js:17
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    DAI: '0x50…0Cb',
    quoted
  • low Secrets in code secret-high-entropy-token src/primitives/pay.js:18
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    USDbC: '0xd9…6Ca',
    quoted
  • low Secrets in code secret-high-entropy-token src/sites/exoskeletons.js:13
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    core: '0x82…a0d',
    quoted
  • low Secrets in code secret-high-entropy-token src/sites/exoskeletons.js:14
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    reader: '0x33…9a5',
    quoted
  • low Secrets in code secret-high-entropy-token src/sites/exoskeletons.js:15
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    reputationOracle: '0xB4…0b4',
    quoted
  • low Secrets in code secret-high-entropy-token src/sites/exoskeletons.js:16
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    outlier: '0x8F…B5C',
    quoted
  • low Secrets in code secret-high-entropy-token src/sites/exoskeletons.js:17
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    board: '0x27…213',
    quoted

Files scanned: 32. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 48/100

  • 0Result and completion. Does not say what the result is
  • 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
  • 30Running it twice. 3 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 100Steps. 11 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1011 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 163: enough signal without eating the budget
  • +4Structure: 10 headings
  • +3Step-by-step instructions: 11 items
  • +4Has examples (4 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.

External checks

ClawHub: suspicious
Reach is a disclosed high-authority web automation skill, but it can move funds, use login sessions, send email, solve CAPTCHAs, and persist sensitive data without enough built-in user controls.
LLM: suspicious (high) · VirusTotal: · 29 May 2026