SKILLEMALL.ai
GitHub ↗ RU Sign in

DB gstack

Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence.

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: OVYED Deno v1.0.0 MIT-0 80 files body ≈ 3 986 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 74/100 · Nearly there — weak spots: inputs and preconditions

IntegrationGitHubAI 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
D
46/100
safety, quality, tests
Safety 60%
21
Quality 40%
84
Run on models
none yet
Process rating
B
74/100
Nearly there
Inputs and preconditions w 11
0
When it triggers w 12
50
Result and completion w 14
60
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.

Broad scope 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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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 · 12

  • high Exfiltration intent-browser-credential-store CHANGELOG.md:235
    Accesses a browser credential / cookie store
    - `cookie-import-browser` command — decrypt and import cookies from real Chromium browsers (Comet, Chrome, Arc, Brave, Edge)
  • high Exfiltration intent-browser-credential-store README.md:76
    Accesses a browser credential / cookie store
    Claude: Imported 8 cookies for staging.myapp.com from Chrome.
  • high Exfiltration intent-browser-credential-store SKILL.md:371
    Accesses a browser credential / cookie store
    | `cookie-import-browser [browser] [--domain d]` | Import cookies from Comet, Chrome, Arc, Brave, or Edge (opens picker, or use --domain for direct import) |
Medium and low: 9
  • medium Exfiltration intent-browser-credential-store ARCHITECTURE.md:9
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    The key insight: an AI agent interacting with a browser needs **sub-second latency** and **persistent state**. If every command cold-starts a browser, you're waiting 3-5 seconds per tool call. If the
    quoted
  • medium Exfiltration intent-browser-credential-store BROWSER.md:69
    Accesses a browser credential / cookie store (code comment)
    │   ├── cookie-import-browser.ts  # Decrypt + import cookies from real Chromium browsers
    comment
  • medium Exfiltration intent-browser-credential-store README.md:27
    Accesses a browser credential / cookie store (documentation table row)
    | `/setup-browser-cookies` | Session manager | Import cookies from your real browser (Comet, Chrome, Arc, Brave, Edge) into the headless session. Test authenticated pages without logging in manually.
    table
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Bash Read AskUserQuestion
  • low Exfiltration read-dotenv CONTRIBUTING.md:105
    Reads a .env file
    # 1. Copy .env.example and add your API key
  • low Exfiltration read-dotenv CONTRIBUTING.md:106
    Reads a .env file
    cp .env.example .env
  • low Dangerous commands cmd-pipe-to-shell-known-host README.md:629
    Pipe-to-shell installer from a well-known host (still executes remote code) (quoted — discussed, not commanded)
    Install it: `curl -fsSL https://bun.sh/install | bash`
    quoted
  • low Dangerous commands cmd-pipe-to-shell-known-host scripts/gen-skill-docs.ts:182
    Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)
    3. If \`bun\` is not installed: \`curl -fsSL https://bun.sh/install | bash\``;
    code literal
  • low Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:106
    Pipe-to-shell installer from a well-known host (still executes remote code) (quoted — discussed, not commanded)
    3. If `bun` is not installed: `curl -fsSL https://bun.sh/install | bash`
    quoted

Files scanned: 17. 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 74/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 50When it triggers. No condition that starts the skill
  • 60Result and completion. Output format stated, no completion criterion
  • 70Failures and branches. 4 branches
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 19 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3986 tokens
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • low 10 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (30 tags): a typed call is more reliable

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)
  • -37 of 7 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 394: enough signal without eating the budget
  • +4Structure: 30 headings
  • +3Step-by-step instructions: 19 items
  • +3Output format is stated explicitly
  • +4Has examples (18 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

External checks

ClawHub: suspicious
Gstack is a coherent engineering automation suite, but it needs Review because it can import real browser sessions, mutate repositories, auto-update itself, and persist workflow data.
LLM: suspicious (high) · VirusTotal: · 29 May 2026