SKILLEMALL.ai
GitHub ↗ RU Sign in

FF ultimate-browsing

Renders, drives, and screenshots web pages: JS-rendered sources, clicks and forms, persistent logins, WAF-blocked hosts (platform-native readers, stealth Chrome), and the browsing lane of a research run, with screenshots as provenance. Not for plain search or unblocked static fetch.

Not recommendedcritical or high security findings · low grade F
code-yeongyu/oh-my-openagent Agent Skills author: code-yeongyu NOASSERTION 58 files · 26 scripts body ≈ 2 550 tokens Open the sourcegithub.com↗ analyzed 4 h ago

Renders, drives, and screenshots web pages: JS-rendered sources, clicks and forms, persistent logins, WAF-blocked hosts (platform-native readers, stealth…

As a process F 44/100 · Will not run — References files that are not bundled: references/insane-search/*.md

GeneratorPlaywrightYouTubeAI and agentsMedia and videoWriting and documentstype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
F
28/100
safety, quality, tests
Safety 60%
0
Quality 40%
71
Run on models
none yet
Process rating
F
44/100
Will not run
References files that are not bundled: references/insane-search/*.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
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.

Concealment
If you install

The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.

For the author

Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".

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.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  3. The text references files that are not there: add them or drop the references.
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 · 29

  • high Concealment en-hide-from-user engine/AGENTS.md:41
    Instruction to hide actions from the user
    never had. A wholesale overwrite with upstream HEAD would silently delete it.
  • high Exfiltration intent-browser-credential-store SKILL.md:29
    Accesses a browser credential / cookie store
    +- login session across pages / inject cookies ------ TIER 2  2b Chrome stealth (profile + cookies)
  • high Exfiltration intent-browser-credential-store SKILL.md:117
    Accesses a browser credential / cookie store
    python3 scripts/extract_cookies.py --browser chrome --domain youtube.com --output ~/.local/state/omo-cookies/youtube.cookies.json
  • high Exfiltration intent-browser-credential-store SKILL.md:119
    Accesses a browser credential / cookie store
    python3 scripts/extract_cookies.py --browser chrome --domain youtube.com --inject --cdp 9242
Medium and low: 25
  • medium Exfiltration intent-browser-credential-store references/agent-reach/social.md:123
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    > **注意**: 服务器 IP 可能遇到 412 错误。使用 `--cookies-from-browser chrome` 或配置代理。
    quoted
  • medium Exfiltration intent-browser-credential-store references/agent-reach/video.md:69
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    > **412 风控**: 海外 IP 必须提供 Cookie（`--cookies-from-browser chrome` 或 `--cookies /path/to/cookies.txt`），国内 IP 一般不受影响。
    quoted
  • medium Exfiltration net-credential-use references/insane-search/jina.md:16
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: Bearer ${JINA_API_KEY}" "https://r.jina.ai/{URL}"
  • medium Exfiltration net-credential-use references/insane-search/json-api.md:48
    Credential used in a network call (verify the destination is the intended service)
    ids = json.load(urllib.request.urlopen('https://hacker-news.firebaseio.com/v0/topstories.json?limitToFirst=5&orderBy=\"\$key\"'))
  • medium Exfiltration intent-browser-credential-store scripts/cookie_paths.py:101
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    db = entry / "cookies.sqlite"
    quoted
  • medium Exfiltration intent-browser-credential-store scripts/extract_cookies.py:10
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    python extract_cookies.py --browser chrome --domain youtube.com --output /tmp/cookies.json
    quoted
  • medium Exfiltration intent-browser-credential-store scripts/extract_cookies.py:11
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    python extract_cookies.py --browser chrome --domain youtube.com --inject --cdp 9242
    quoted
  • medium Exfiltration intent-browser-credential-store scripts/extract_cookies.py:258
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    print(f"Injected {ok}/{len(filtered)} cookies into local Chrome (playwright-core CDP {cdp_port})")
    quoted
  • medium Exfiltration intent-browser-credential-store SKILL.md:112
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    `scripts/extract_cookies.py` reads cookies from a local Chromium-family or Firefox-family browser and optionally injects them into the running CDP session. It resolves browser profile paths and decryp
    quoted
  • low Obfuscation obf-base64-blob engine/tests/fixtures/search_interstitial.html:7
    Long base64-looking blob (detector / deny-list definition; security demo / example; test fixture / example file)
    '*/var yt=153,T=function(y,x,Y,E,t,Z,W,f,n,p,V){(y&125)==y&&(p=(Y|7)- -1+(~Y^7),n=d5,t=[-82,48,-20,-47,74,-64,t,-71,-52,80],W=Nu[E.l](E.Du),W[E.l]=function(P){f=(p+=6+7*Y,p&=7,P)},W.concat=function(P,
    detectordemofixture
  • low Obfuscation obf-hex-escape-chain engine/tests/fixtures/search_interstitial.html:7
    Escaped/char-code string obfuscation (detector / deny-list definition; security demo / example; test fixture / example file)
    '*/var yt=153,T=function(y,x,Y,E,t,Z,W,f,n,p,V){(y&125)==y&&(p=(Y|7)- -1+(~Y^7),n=d5,t=[-82,48,-20,-47,74,-64,t,-71,-52,80],W=Nu[E.l](E.Du),W[E.l]=function(P){f=(p+=6+7*Y,p&=7,P)},W.concat=function(P,
    detectordemofixture
  • low Secrets in code secret-high-entropy-token engine/tests/fixtures/search_interstitial.html:7
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; test fixture / example file)
    '*/var yt=153,T=function(y,x,Y,E,t,Z,W,f,n,p,V){(y&125)==y&&(p=(Y|7)- -1+(~Y^7),n=d5,t=[-82,48,-20,-47,74,-64,t,-71,-52,80],W=Nu[E.l](E.Du),W[E.l]=function(P){f=(p+=6+7*Y,p&=7,P)},W.concat=function(P,
    detectorfixture
  • low Secrets in code secret-high-entropy-token engine/tests/fixtures/wayback_snapshot.html:20
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    "wgPageContentModel":"wikitext","wgRelevantPageName":"Web_archiving","wgRelevantArticleId":6014932,"wgIsProbablyEditable":true,"wgRelevantPageIsProbablyEditable":true,"wgRestrictionEdit":[],"wgRestric
    fixturequoted
  • low Obfuscation obf-hex-escape-chain engine/tests/fixtures/wayback_snapshot.html:472
    Escaped/char-code string obfuscation (detector / deny-list definition; security demo / example; test fixture / example file)
    <li class="interlanguage-link interwiki-ar mw-list-item"><a href="https://web.archive.org/web/20241227132135/https://ar.wikipedia.org/wiki/%D8%A3%D8%B1%D8%B4%D9%81%D8%A9_%D8%A7%D9%84%D9%88%D9%8A%D8%A8
    detectordemofixture
  • low Secrets in code secret-high-entropy-token engine/tests/fixtures/wayback_snapshot.html:748
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    <li id="cite…a-3"><span class="mw-cite-backlink">^ <a href="#cite…3-0"><sup><i><b>a</b></i></sup></a> <a href="#cite…3-1"><sup><i><b>b</b></i></sup></a>
    fixturequoted
  • low Secrets in code secret-high-entropy-token engine/tests/fixtures/wayback_snapshot.html:750
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    <li id="cite_note-4"><span class="mw-cite-backlink"><b><a href="#cite_ref-4">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-d…821
    fixturequoted
  • low Secrets in code secret-high-entropy-token engine/tests/fixtures/wayback_snapshot.html:778
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    <li id="cite…-18"><span class="mw-cite-backlink"><b><a href="#cite_ref-18">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-d…238
    fixturequoted
  • low Exfiltration intent-browser-credential-store scripts/cookie_paths.py:104
    Accesses a browser credential / cookie store (negated — the text forbids it)
    raise FileNotFoundError(f"no cookies.sqlite under {profile_root}")
    negated
  • low Exfiltration intent-browser-credential-store scripts/tests/test_cookie_domain_filter.py:62
    Accesses a browser credential / cookie store (test fixture / example file; quoted — discussed, not commanded)
    "Google/Chrome/User Data/Default/Cookies",
    fixturequoted
  • low Exfiltration intent-browser-credential-store scripts/tests/test_cookie_domain_filter.py:87
    Accesses a browser credential / cookie store (test fixture / example file; quoted — discussed, not commanded)
    "Firefox/Profiles/abc.default/cookies.sqlite",
    fixturequoted
  • low Exfiltration intent-browser-credential-store scripts/tests/test_extract_cookies.py:68
    Accesses a browser credential / cookie store (detector / deny-list definition; security demo / example; test fixture / example file)
    target = base / "Google/Chrome/Default/Cookies"
    detectordemofixture
  • low Exfiltration intent-browser-credential-store scripts/tests/test_extract_cookies.py:75
    Accesses a browser credential / cookie store (detector / deny-list definition; security demo / example; test fixture / example file)
    target = base / "google-chrome/Default/Network/Cookies"
    detectordemofixture
  • low Exfiltration intent-browser-credential-store scripts/tests/test_extract_cookies.py:82
    Accesses a browser credential / cookie store (detector / deny-list definition; security demo / example; test fixture / example file)
    target = base / "Google/Chrome/User Data/Default/Cookies"
    detectordemofixture
  • low Exfiltration intent-browser-credential-store scripts/tests/test_extract_cookies.py:147
    Accesses a browser credential / cookie store (test fixture / example file; quoted — discussed, not commanded)
    "Google/Chrome/Default/Cookies",
    fixturequoted
  • low Exfiltration intent-browser-credential-store scripts/tests/test_extract_cookies.py:160
    Accesses a browser credential / cookie store (test fixture / example file; quoted — discussed, not commanded)
    "Firefox/Profiles/abc.default/cookies.sqlite",
    fixturequoted

Files scanned: 57. 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")
  • warning missing-ref reference to a missing file: references/insane-search/*.md

Process rating: all ten parameters 44/100

Will not run. References files that are not bundled: references/insane-search/*.md
  • 0Tools and files. 1 referenced file(s) missing: references/insane-search/*.md
  • 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
  • 30Running it twice. 3 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 85Steps. 7 steps, 1 vague phrases
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2550 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
  • +3Output format is not stated: the model decides each time
  • -33 of 4 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 283: enough signal without eating the budget
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 7 items
  • +4Has examples (6 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.