SKILLEMALL.ai
GitHub ↗ RU Sign in

DC unbrowse

Analyze any website's network traffic and turn it into reusable API skills backed by a shared marketplace. Skills discovered by any agent are published, scored, and reusable by all agents. Capture network traffic, discover API endpoints, learn patterns, execute learned skills, and manage auth for gated sites. Use when someone wants to extract structured data from a website, discover API endpoints, automate web interactions, or work without official API documentation.

Not recommendedcritical or high security findings · low grade D
modbender/skill-library-mcp Agent Skills author: modbender MIT 80 files body ≈ 1 907 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Analyze any website's network traffic and turn it into reusable API skills backed by a shared marketplace.

As a process C 54/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationAI 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
D
54/100
safety, quality, tests
Safety 60%
36
Quality 40%
82
Run on models
none yet
Process rating
C
54/100
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

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.

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 · 27

  • high Exfiltration intent-browser-credential-store SKILL.md:132
    Accesses a browser credential / cookie store
    **Automatic.** Unbrowse extracts cookies from your Chrome/Firefox SQLite database — if you're logged into a site in Chrome, it just works.
Medium and low: 26
  • medium Exfiltration intent-browser-credential-store src/api/routes.ts:164
    Accesses a browser credential / cookie store (code comment)
    // POST /v1/auth/steal — extract cookies from Chrome/Firefox SQLite DBs.
    comment
  • medium Exfiltration intent-browser-credential-store src/auth/browser-cookies.ts:2
    Accesses a browser credential / cookie store (code comment)
    * Extract cookies directly from Chrome/Firefox SQLite databases.
    comment
  • medium Exfiltration intent-browser-credential-store src/auth/browser-cookies.ts:71
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    const candidate = join(profilesRoot, profile, "cookies.sqlite");
    quoted
  • medium Exfiltration intent-browser-credential-store src/auth/browser-cookies.ts:78
    Accesses a browser credential / cookie store (detector / deny-list definition)
    const candidate = join(profilesRoot, targetDir, "cookies.sqlite");
    detector
  • medium Exfiltration intent-browser-credential-store src/auth/index.ts:117
    Accesses a browser credential / cookie store (code comment)
    * Extract cookies directly from Chrome/Firefox SQLite databases.
    comment
  • low Secrets in code secret-high-entropy-token traces/-u6tyne-nwFmmPHiX7_P7.json:263
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "acce…sV2": {
    quoted
  • low Secrets in code secret-high-entropy-token traces/17_IxVu6EnQsSIdWFbt_T.json:11
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "D1wZ…BLV",
    quoted
  • low Secrets in code secret-high-entropy-token traces/17_IxVu6EnQsSIdWFbt_T.json:16
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "dev": "Hb6C…d5a",
    detector
  • low Secrets in code secret-high-entropy-token traces/17_IxVu6EnQsSIdWFbt_T.json:19
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "tokenProgram": "Toke…5DA",
    quoted
  • low Secrets in code secret-high-entropy-token traces/17_IxVu6EnQsSIdWFbt_T.json:22
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "partnerConfig": "7SXE…SDn",
    quoted
  • low Secrets in code secret-high-entropy-token traces/17_IxVu6EnQsSIdWFbt_T.json:24
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "D1wZ…BLV",
    quoted
  • low Secrets in code secret-high-entropy-token traces/2Mey1qFGJIV_XvM-LcGo6.json:428
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "logo": "2024…eck Logo 600x600 1.png",
    quoted
  • low Secrets in code secret-high-entropy-token traces/2Mey1qFGJIV_XvM-LcGo6.json:1650
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "logo": "2025…est 1.png",
    quoted
  • low Secrets in code secret-high-entropy-token traces/2Mey1qFGJIV_XvM-LcGo6.json:1975
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "logo": "2025…ons Logo Navy High Res.png",
    quoted
  • low Secrets in code secret-high-entropy-token traces/8LDnk7QyUWv7PVWY9cfKP.json:12
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "pool_address": "E5H5…ya8",
    quoted
  • low Secrets in code secret-high-entropy-token traces/8LDnk7QyUWv7PVWY9cfKP.json:14
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "DBRi…Uu5",
    quoted
  • low Secrets in code secret-high-entropy-token traces/8LDnk7QyUWv7PVWY9cfKP.json:15
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "EPjF…t1v"
    quoted
  • low Secrets in code secret-high-entropy-token traces/8LDnk7QyUWv7PVWY9cfKP.json:26
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "2N1j…SLW",
    quoted
  • low Secrets in code secret-high-entropy-token traces/8LDnk7QyUWv7PVWY9cfKP.json:27
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "3ESU…mHQ"
    quoted
  • low Secrets in code secret-high-entropy-token traces/AlNyzqyrTiroVMgW5kMGU.json:9
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    "result": "<!DOCTYPE html><!--Mn…a--><html lang=\"en\"><head><meta charSet=\"utf-8\"/><meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\"/><meta name=\"viewport\
    placeholder
  • low Secrets in code secret-high-entropy-token traces/cKnV2qlLr6EvR50VA0omD.json:11
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "So11…112": []
    quoted
  • low Secrets in code secret-high-entropy-token traces/eF_oOt7OkDa7RYox_4IGr.json:11
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "EPjF…t1v",
    quoted
  • low Secrets in code secret-high-entropy-token traces/eF_oOt7OkDa7RYox_4IGr.json:19
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "dev": "5TYZ…dGj",
    quoted
  • low Secrets in code secret-high-entropy-token traces/eF_oOt7OkDa7RYox_4IGr.json:22
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "tokenProgram": "Toke…5DA",
    quoted
  • low Secrets in code secret-high-entropy-token traces/eF_oOt7OkDa7RYox_4IGr.json:23
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "mintAuthority": "BJE5…ruG",
    quoted
  • low Secrets in code secret-high-entropy-token traces/eF_oOt7OkDa7RYox_4IGr.json:24
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "freezeAuthority": "7dGb…rar",
    quoted

Files scanned: 80. 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 54/100

  • 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
  • 30Running it twice. 1 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 40Consistency. Frontmatter name (unbrowse) differs from the folder (unbrowse-openclaw)
  • 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
  • 100Steps. 8 steps
  • 100Failures and branches. 2 branches, has a failure section
  • 100Execution cost. Instruction body is 1907 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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 471: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 8 items
  • +4Has examples (11 code blocks)

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