claude-blog

Why this score

Popularity score: 85/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

Security

Scanned Oct 22, 2026 at commit aec971ac5113, first 300 source files (it's a large repo), with Cisco's open-source skill-scanner.

What its code does:

• Reads environment variables and sends network requests with them API clients do this to send your key to the service. Check which service it talks to.brain/.raw/sources/claude-blog-skill/scripts/blog_preflight.py, brain/.raw/sources/claude-blog-skill/scripts/generate_hero.py, scripts/blog_preflight.py and 6 more
• Runs shell commands Common for dev tools. Read the commands it runs.CHANGELOG.md:1, docs/INSTALLATION.md:1, install.sh:1 and 6 more
• Runs code it builds while running (eval or exec) Harder to read ahead of time, since the code is assembled while it runs.brain/scripts/audit_brain.py
• Makes network requestsbrain/.raw/sources/claude-blog-skill/scripts/blog_preflight.py:689, brain/.raw/sources/claude-blog-skill/scripts/generate_hero.py:221, brain/.raw/sources/claude-blog-skill/scripts/sync_flow.py:148 and 10 more
• Uses dependencies without a pinned version A later version of a dependency could change what runs.pyproject.toml:38 and 19 more
• Includes scripts in hidden folders Folders starting with a dot are easy to miss when you read a repo.brain/.raw/sources/claude-blog-skill/scripts/ai_citation_score.py, brain/.raw/sources/claude-blog-skill/scripts/analyze_blog.py, brain/.raw/sources/claude-blog-skill/scripts/blog_hygiene.py and 15 more

Web addresses in its code:

• googleapis.comskills/blog-google/scripts/ga4_report.py:46
• aistudio.google.cominstall.ps1:258
• notebooklm.google.comskills/blog-notebooklm/scripts/auth_manager.py:140
• oauth2.googleapis.comskills/blog-google/scripts/google_auth.py:315
• raw.githubusercontent.comscripts/validate_public_release.py:25
• api.dataforseo.comskills/blog-cannibalization/SKILL.md:92
• api.github.combrain/.raw/sources/claude-blog-skill/scripts/sync_flow.py:32
• api.openverse.engineeringbrain/.raw/sources/claude-blog-skill/scripts/generate_hero.py:43
• api.pexels.combrain/.raw/sources/claude-blog-skill/scripts/generate_hero.py:45
• api.unsplash.combrain/.raw/sources/claude-blog-skill/scripts/generate_hero.py:44
• chromeuxreport.googleapis.comskills/blog-google/scripts/crux_history.py:33
• pixabay.combrain/.raw/sources/claude-blog-skill/scripts/generate_hero.py:46
• youtube.comskills/blog-google/scripts/youtube_search.py:132
• accounts.google.comskills/blog-google/scripts/google_auth.py:428
• ads.google.comskills/blog-google/scripts/keyword_planner.py:69

And 3 more.

These are the sites named in the code, so it's where your data could go. It isn't a complete list: code can build addresses while it runs, and a few of these may be links rather than calls. Whatever you send also goes to the AI model you use.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.