Skip to content
Good for Bots

Safe Outreach

safe-outreach.com

Checks Chrome extensions against LinkedIn's detection list, with code teardowns of outreach tools

Click badge to copy

Changed your site? Run a new scan.

Claim to rescan

Claiming is free. Verify ownership to request a rescan after deploying your changes.

Unclaimed listings are checked automatically every 90 days.

Good for Bots report

Safe Outreach scores 91 of 100: the whole readable base, 41 of the 50 agent-layer points, no penalties.

Earned

The whole readable base above the line, 41 of the 50 agent-layer points below it.

91

2 prompts away

Copy them below ↓

9
Penalties0
How scoring works · current methodology →

Through a bot’s eyes

“Safe Outreach is a site that checks whether a Chrome extension is on LinkedIn's Active Extension Detection list and publishes code-level teardowns of LinkedIn automation and outreach extensions, including where each sends a user's LinkedIn session.”

Simulated from the response GoodForBotsBot received on , not a live answer from any AI assistant.

What it can read, and what stays hidden →

What a bot can read

The homepage text covers LinkedIn's AED list and its 4,934 entries, the checker, a set of popular LinkedIn automation extensions with user counts and detection status, the difference between local-scrape and cookie-bridge session handling, data-flow diagrams for individual tools, LinkedIn search-volume figures, and a list of teardowns. The text is attributed to Safe Outreach and dated November 7, 2026. The Markdown version repeats this content with front matter that adds publication and modification dates and a canonical URL. The llms.txt file gives a short summary of the site and a list of key pages, including a line for each extension covering AED listing and where the session goes. The JSON-LD adds the site name, description, organisation logo and a search action for checking a tool name. Together these give a model the same subject matter as the homepage in more structured form, without pricing or contact details.

What stays hidden

A model reading this input cannot find what the checker or the teardowns cost, or whether they are free. The input gives only the publisher name Safe Outreach, with no contact address or named author. The homepage shows only a sample of tool verdicts, so it cannot tell whether a given extension is covered. The methodology and the reasoning behind each verdict are only summarised, and they sit on linked pages that were not read.

What is Safe Outreach?

Safe Outreach is a website that checks whether a Chrome extension appears on LinkedIn's Active Extension Detection (AED) list, a set of 4,934 extension IDs that the input says is embedded in LinkedIn's frontend code as of its November 2026 snapshot. Visitors can type an extension's name or Chrome Web Store URL to see whether it is listed.

Read more →

The site also publishes code teardowns of LinkedIn automation, scraping and outreach extensions, covering where each tool sends a user's LinkedIn session: to a vendor's cloud or stays in the browser. The input says the publisher has read the code of 100+ tools. The homepage refers to people who worry about LinkedIn restrictions, though it does not state pricing or a formal audience.

3 prompts, 9 points

For Claude Code, Cursor or Codex. The score moves after the next scan.

+5score from 91 to 96

State a position on AI crawlers

robots.txt states AI usage preferences, but names no AI crawler individually.

Read prompt

+3.8score from 96 to 100

Add descriptions to llms.txt

/llms.txt is partly descriptive: only 43% of links carry a description. 115 of 120 descriptions follow the link with something other than ":", the separator the format specifies (`- [name](url): notes`).

Read prompt

+1 capabilitybadge capabilities from 3 to 4

Publish an auth.md for agents

No /auth.md published.

Read prompt

Pro

7 more prompts in Pro

Pro shows a prompt for every fix and drafts your llms.txt and robots.txt. It never changes the score.

$9 once, per listingSee Pro

Deployed your fixes? Rescan to update your score →

Ready-made files

Pro drafts these for this site.

Pro

A ready-made llms.txt and robots.txt

Pro drafts both files for Safe Outreach from its scan, keeps only links and rules our parsers can verify, and hands them over ready to review and publish. It never changes the score.

See Pro

Select a check to see what we found and how it is graded.

Readable base

50 / 50

Passes.

3.3 of 3.3 points.

robots.txt is valid, with 1 user-agent group.

Passes.

8.3 of 8.3 points.

Sitemap declared in robots.txt, listing 158 URLs.

Passes.

8.3 of 8.3 points.

All 4 pages read pass. The homepage describes itself to machines as WebPage, Organization, ImageObject in valid schema.org JSON-LD.

Passes.

10 of 10 points.

All 4 pages read pass. The homepage marks its content root, its heading outline and its landmarks.

Passes.

8.3 of 8.3 points.

15 of 15 assessed homepage navigation links expose usable destinations.

Passes.

4.2 of 4.2 points.

610 of 610 assessed homepage links and buttons have a nonempty accessible name.

Passes.

2.5 of 2.5 points.

1 of 1 assessed homepage form fields meet the static naming and field-semantics checks.

Passes.

2.5 of 2.5 points.

613 of 613 assessed homepage controls and role declarations meet the static role, state and relationship checks.

Passes.

1.7 of 1.7 points.

All 4 pages read pass. The homepage declares itself as its canonical URL.

Agent layer

41.3 / 50

Passes.

11.3 of 11.3 points.

/llms.txt is well formed: 278 links across 4 sections.

Half passes.

3.8 of 7.5 points.

/llms.txt is partly descriptive: only 43% of links carry a description. 115 of 120 descriptions follow the link with something other than ":", the separator the format specifies (`- [name](url): notes`).

Passes.

12.5 of 12.5 points.

llms.txt points at 278 markdown versions of pages.

Passes.

10 of 10 points.

All 4 pages read pass. The homepage serves markdown on `Accept: text/markdown`.

Fails.

0 of 5 points.

robots.txt states AI usage preferences, but names no AI crawler individually.

Passes.

2.5 of 2.5 points.

Declares AI usage preferences via Content-Signal (robots.txt): ai-train, ai-input, search.

Penalties

− 0

Passes.

Penalty: 0 of 15 points.

Our crawler reaches the page without being challenged.

Passes.

Penalty: 0 of 20 points.

Nothing on the homepage tells a crawler to skip it or to withhold its snippet.

Passes.

Penalty: 0 of 25 points.

The captured homepage HTML contains 2606 content words; completeness is not assessed.

Passes.

Penalty: 0 of 25 points.

robots.txt allows every known search and user-fetch crawler to reach the homepage.

Passes.

Penalty: 0 of 10 points.

The homepage is served over HTTPS and returns HTTP 200.

Passes.

Penalty: 0 of 3 points.

The homepage provides both a non-empty title and meta description.

Passes.

Penalty: 0 of 3 points.

The homepage is reached in 0 redirects.

Passes.

Penalty: 0 of 3 points.

The homepage reached a plain crawler in 49 ms.

Agent capabilities

3 of 11 · no points

Each one found adds +1 to the badge.

Passes.

+1 on the badge.

Publishes an API catalog describing 1 API.

Not applicable.

Adds +1 to the badge when found.

No /auth.md published.

Not applicable.

Adds +1 to the badge when found.

No AI Catalog published, so no MCP server card can be discovered.

Passes.

+1 on the badge.

Publishes an A2A Agent Card at /.well-known/agent-card.json, with 1 A2A interface; the card departs from the A2A specification in 1 place.

Passes.

+1 on the badge.

Publishes an Agent Skills index with 1 usable entry. Skill artifacts and digests were not verified.

Not applicable.

Adds +1 to the badge when found.

No WebMCP declarations were found in the collected HTML or inline scripts. External scripts were not inspected.

Not applicable.

Adds +1 to the badge when found.

No Web Bot Auth key directory at /.well-known/http-message-signatures-directory.

Not applicable.

Adds +1 to the badge when found.

No HTTP 402 payment challenge on the homepage or robots.txt, and no manifest at /.well-known/x402.

Not applicable.

Adds +1 to the badge when found.

No ACP discovery declaration established at /.well-known/acp.json.

Not applicable.

Adds +1 to the badge when found.

No UCP discovery declaration established at /.well-known/ucp.

Not applicable.

Adds +1 to the badge when found.

No public AMP discovery declaration established. Private or hidden agents may not advertise one to our crawler.

Access & usage policy

Who can read this page, and for what purpose?

GoodForBotsBot received HTTP 200 via a direct request. No indexing restriction was observed in the supported homepage directives.

Sampled URL: https://safe-outreach.com/

Declared crawling rules

No matching refusal for this URL was found for the listed identities.

Sources and scope: declared crawling rules
  • Declared allow · Scan admission

    • GoodForBotsBot/1.0 (+https://goodforbots.com/bot)

    The recorded robots admission decision allowed our crawler to proceed.

    GoodForBotsBot admission along the homepage request chain

    https://safe-outreach.com/

    robots.txt is present and valid

  • Declared allow · robots.txt

    • goodforbotsbot (Site diagnostics)
    • * (Default robots group)
    • oai-searchbot (ai-search)
    • claude-searchbot (ai-search)
    • perplexitybot (ai-search)
    • mistralai-index (ai-search)
    • kimi-searchbot (ai-search)
    • amzn-searchbot (ai-search)
    • meta-webindexer (ai-search)
    • exasearchbot (ai-search)
    • aiwebindex (ai-search)
    • duckassistbot (ai-search)
    • shapbot (ai-search)
    • yandexadditional (ai-search)
    • yandexadditionalbot (ai-search)
    • gptbot (ai-training)
    • claudebot (ai-training)
    • mistralai-training (ai-training)
    • kimibot (ai-training)
    • ai2bot (Unknown)
    • applebot-extended (ai-training)
    • webzio-extended (ai-training)
    • chatgpt-user (user-fetch)
    • claude-user (user-fetch)
    • perplexity-user (user-fetch)
    • mistralai-user (user-fetch)
    • kimi-user (user-fetch)
    • amzn-user (user-fetch)
    • diffbot-user (user-fetch)
    • firecrawlagent (extraction)
    • webzio (extraction)
    • meta-externalfetcher (user-fetch, agent)
    • google-extended (ai-training, grounding)
    • meta-externalagent (ai-training, product-improvement)
    • amazonbot (ai-training, product-improvement)
    • ccbot (open-dataset, ai-training)
    • googlebot (search)
    • bingbot (search)

    No matching refusal for this URL in the applicable robots group. This is a declaration, not an access test.

    Acquisition of https://safe-outreach.com/

    https://safe-outreach.com/robots.txt

    User-agent: *
    allow: /

    robots.txt is present and validStates a position on AI crawlersAllows search and user-fetch crawlers

Observed access

GoodForBotsBot received HTTP 200 via a direct request.

Sources and scope: observed access
Coverage and interpretation
  • Crawler coverage includes the registered identities and up to 50 user-agent entries from robots.txt. Source excerpts and detail groups are bounded; omissions are labelled.
  • Observed access describes GoodForBotsBot only. Other crawler entries describe declared rules, not tests of those operators' access.
  • Coverage is the sampled homepage response and collected robots.txt files. No indexing or citation is guaranteed. Usage preferences are declarations, not a legal determination of permission.
  • This explanation adds no points or penalties. Any score effects belong to the linked checks.
  • AIPREF and Content Signals keep their own definitions. AIPREF search can include processing used exclusively for search; training preferences are not a blanket ruling on every search process.

In its category

1st of 7 in Research & Reference

  1. 1Safe Outreach · this reportsafe-outreach.com
  2. 2Can I 3D Print It?cani3dprintit.com
  3. 3Shift at Midnight Field Manualshiftatmidnightwiki.com

Category average 69. The percentile appears once the catalogue holds a few hundred sites.

Scanned

Site profile

Login
Not established
API
Detected
An API catalog
Commerce
Not established

It decides which conditional checks apply. “Not established” means no proof in what we read, not proof of absence.

Scan details

Every scan is kept. Pro draws the history as a chart →

Scanned
7 Nov 2026
Rubric
0.9.0
Requests
23
Fetched
2 MB
Took
14.9 s
Homepage
49 ms · direct
Pages read
4
robots.txt
allowed
Which pages the scan read

The homepage and up to three pages from the sitemap and homepage links. Structured data, page structure, Markdown negotiation and typed links check each page read and take the median page; other checks read the homepage.

  • Homepagealways read
  • /best-linkedin-automation-toolsarticle · linked from the homepage · from the sitemap · read
  • /aboutabout · linked from the homepage · from the sitemap · read
  • /deep-diveslinked from the homepage · from the sitemap · read

More like Safe Outreach:Research & ReferenceSalesSecurity & Privacy

dolaai.pro

AI agent that edits Unreal Engine 5.7 Blueprints, C++ and levels in the open editor

saascubes.com

Curated SaaS directory offering permanent do-follow backlinks for modern software products

Also Excellent

goodforbots.com

Evaluates website readability for AI crawlers and language models with a scoring rubric

Also Excellent

contentspilot.com

AI co-pilot that plans, drafts and schedules Instagram carousels and posts in brand style

Also Excellent

brivoy.com

Community site where makers launch new products and early adopters discover them

vouchgeo.com

Tracks how AI assistants mention a brand across multi-question buying conversations