SKILLEMALL.ai
RU Sign in

CC browser-control

Remote browser access for login, 2FA, captcha, and manual verification. Protected by Google OAuth - only the configured email can access. Use when you need the user to log into a website, complete 2FA/MFA, solve a captcha, or do any manual browser action.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: Felipe Goulu v1.0.3 6 files · 5 scripts body ≈ 823 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions

AnalyzerData and analyticsAI and agentstype 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%
62
Quality 40%
82
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
50
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
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.

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

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
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

  • high Exfiltration exfil-webhook-url SKILL.md:88
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    Open: https://xxx.ngrok.app/vnc.html?password=xxx&autoconnect=true
Medium and low: 4
  • medium Dangerous commands cmd-privilege install.sh:73
    Privilege escalation / world-writable permissions
    curl -s https://ngro…com/ngrok.asc | sudo tee /etc/apt/trusted.gpg.d/ngrok.asc >/dev/null
  • medium Dangerous commands cmd-privilege install.sh:74
    Privilege escalation / world-writable permissions
    echo "deb https://ngro…com buster main" | sudo tee /etc/apt/sources.list.d/ngrok.list
  • medium Exfiltration exfil-webhook-url SKILL.md:61
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    "novncUrl": "https://xxx.ngrok.app/vnc.html?password=xxx&autoconnect=true",
    quoted
  • medium Exfiltration exfil-webhook-url SKILL.md:62
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    "tunnelUrl": "https://xxx.ngrok.app",
    quoted

Files scanned: 6. 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 57/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 50When it triggers. No condition that starts the skill
  • 55Failures and branches. 1 branches
  • 60Tools and files. Uses tools (bash, read) that frontmatter does not declare
  • 100Steps. 23 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 823 tokens
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 11 top-level sections: this looks like several domains in one skill

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
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 255: enough signal without eating the budget
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 23 items
  • +4Has examples (8 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.

External checks

ClawHub: suspicious
This skill has a coherent remote-browser purpose, but it exposes high-impact browser/desktop access and under-discloses how sensitive the access link and session control are.
LLM: suspicious (high) · VirusTotal: suspicious · 27 May 2026