From c7caccd3fba25f96bbd0fe6aafbfbe3ea397f29d Mon Sep 17 00:00:00 2001 From: s0lray Date: Fri, 27 Mar 2026 09:14:57 -0400 Subject: [PATCH] Enrich Search Engines batch 2/4: code search, FTP, academic tools (THE-152) Populate enrichment fields (description, status, pricing, bestFor, input, output, opsec, opsecNote, and all badge booleans) for 25 Search Engines tools across Code Search, FTP Search, and Academic/Publication Search subcategories. Notable findings: - OpenGrey EU Papers: marked deprecated (archived 2020, INIST-CNRS discontinued) - US Gov Publishing Office - FDsys: marked deprecated (superseded by GovInfo) - Think Tank Search: marked deprecated (service discontinued Feb 2025) - GitLeaks, Gitrob, Github-Dorks: active OPSEC (query GitHub API/clone repos) - All 22 live tools verified operational Co-Authored-By: Paperclip --- public/arf.json | 425 +++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 400 insertions(+), 25 deletions(-) diff --git a/public/arf.json b/public/arf.json index b8b4568..eb675b0 100644 --- a/public/arf.json +++ b/public/arf.json @@ -4889,27 +4889,102 @@ { "name": "Searchcode", "type": "url", - "url": "https://searchcode.com/" + "url": "https://searchcode.com/", + "description": "Code search engine that indexes public source code from GitHub, GitLab, Bitbucket, and other repositories; useful for finding code examples and identifying technology usage patterns.", + "status": "live", + "pricing": "freemium", + "bestFor": "Source code snippet and function discovery across public repositories", + "input": "Code snippet, function name, or keyword", + "output": "Matching source code files with context and repository links", + "opsec": "passive", + "opsecNote": "Searches are routed through Searchcode's servers; no direct contact with target repositories.", + "localInstall": false, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": true, + "invitationOnly": false, + "deprecated": false }, { "name": "NerdyData", "type": "url", - "url": "https://www.nerdydata.com/reports/new" + "url": "https://www.nerdydata.com/reports/new", + "description": "Source code search engine for website technology reconnaissance that indexes HTML, CSS, and JavaScript across millions of live websites to identify technology and library usage.", + "status": "live", + "pricing": "freemium", + "bestFor": "Identifying websites using specific technologies, libraries, or code patterns", + "input": "Code snippet, library name, or technology string", + "output": "List of websites containing matching source code", + "opsec": "passive", + "opsecNote": "Searches NerdyData's pre-built index; no direct contact with target websites.", + "localInstall": false, + "googleDork": false, + "registration": true, + "editUrl": false, + "api": false, + "invitationOnly": false, + "deprecated": false }, { "name": "Gitrob (T)", "type": "url", - "url": "https://github.com/michenriksen/gitrob" + "url": "https://github.com/michenriksen/gitrob", + "description": "CLI tool for reconnaissance on GitHub organizations and users; clones repositories and scans commit history for sensitive files, exposed credentials, and configuration data.", + "status": "live", + "pricing": "free", + "bestFor": "GitHub organization reconnaissance for exposed secrets and sensitive files in commit history", + "input": "GitHub username or organization name", + "output": "List of potentially sensitive files and paths found across repositories", + "opsec": "active", + "opsecNote": "Directly queries the GitHub API and clones repositories; API activity is logged and may alert security monitoring.", + "localInstall": true, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": false, + "invitationOnly": false, + "deprecated": false }, { "name": "Github-Dorks (T)", "type": "url", - "url": "https://github.com/techgaun/github-dorks" + "url": "https://github.com/techgaun/github-dorks", + "description": "Collection of GitHub advanced search operators and a CLI tool that automates searching GitHub for exposed credentials, API keys, configuration files, and other sensitive information.", + "status": "live", + "pricing": "free", + "bestFor": "Finding exposed credentials and sensitive files on GitHub via advanced search dorks", + "input": "Target username, organization, or domain", + "output": "GitHub search results matching dork patterns for sensitive data exposure", + "opsec": "active", + "opsecNote": "Queries the GitHub search API; activity is logged by GitHub and may trigger alerts for repository owners.", + "localInstall": true, + "googleDork": true, + "registration": false, + "editUrl": false, + "api": false, + "invitationOnly": false, + "deprecated": false }, { "name": "GitLeaks", "type": "url", - "url": "https://github.com/gitleaks/gitleaks" + "url": "https://github.com/gitleaks/gitleaks", + "description": "Open-source SAST tool for detecting hardcoded secrets, API keys, passwords, and credentials in git repositories and file systems using customizable regex-based detection rules.", + "status": "live", + "pricing": "free", + "bestFor": "Scanning git repositories for hardcoded secrets, API keys, and leaked credentials", + "input": "Git repository path, remote URL, or file system path", + "output": "Report of detected secrets with file location, matched rule, commit hash, and line context", + "opsec": "active", + "opsecNote": "Remote scans require cloning the target repository; clone activity may be logged by the hosting platform.", + "localInstall": true, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": false, + "invitationOnly": false, + "deprecated": false } ] }, @@ -4920,17 +4995,62 @@ { "name": "GlobalFile", "type": "url", - "url": "https://globalfilesearch.com/" + "url": "https://globalfilesearch.com/", + "description": "FTP file search engine that indexes publicly accessible FTP servers; allows searching for specific file types including images, videos, software, and archives.", + "status": "live", + "pricing": "free", + "bestFor": "Discovering publicly accessible files on FTP servers by filename or file type", + "input": "Filename, file extension, or keyword", + "output": "List of matching files with FTP server addresses and paths", + "opsec": "passive", + "opsecNote": "Searches GlobalFile's pre-built index of FTP servers; no direct connection to target FTP servers.", + "localInstall": false, + "googleDork": false, + "registration": false, + "editUrl": true, + "api": false, + "invitationOnly": false, + "deprecated": false }, { "name": "FTP Google Dork (D)", "type": "url", - "url": "https://www.google.com/search?q=inurl%3Aftp+-inurl%3Ahttp+-inurl%3Ahttps+ftpsearchterm" + "url": "https://www.google.com/search?q=inurl%3Aftp+-inurl%3Ahttp+-inurl%3Ahttps+ftpsearchterm", + "description": "Google dork technique using inurl:ftp operators to discover publicly indexed FTP server directories and files through Google's web index.", + "status": "live", + "pricing": "free", + "bestFor": "Discovering publicly indexed FTP server directories and files via Google dorking", + "input": "Search term appended to the dork URL", + "output": "Google search results showing indexed FTP server directories", + "opsec": "passive", + "opsecNote": "Searches are routed through Google; no direct contact with target FTP servers.", + "localInstall": false, + "googleDork": true, + "registration": false, + "editUrl": true, + "api": false, + "invitationOnly": false, + "deprecated": false }, { "name": "Napalm FTP", "type": "url", - "url": "https://www.searchftps.net/" + "url": "https://www.searchftps.net/", + "description": "FTP indexer and search engine with over 329 million files indexed across 1,200+ FTP servers; supports advanced filtering by file type, size, and server location.", + "status": "live", + "pricing": "free", + "bestFor": "Large-scale FTP file discovery across hundreds of indexed public servers", + "input": "Filename, file type, or keyword", + "output": "Matching files with FTP server address, path, file size, and date", + "opsec": "passive", + "opsecNote": "Searches Napalm FTP's index; no direct connection to target FTP servers during search.", + "localInstall": false, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": false, + "invitationOnly": false, + "deprecated": false } ] }, @@ -4941,87 +5061,342 @@ { "name": "PubPeer", "type": "url", - "url": "https://pubpeer.com/" + "url": "https://pubpeer.com/", + "description": "Post-publication peer review platform where researchers comment on and flag issues with published scientific papers; useful for identifying retracted or problematic research.", + "status": "live", + "pricing": "free", + "bestFor": "Verifying scientific publication credibility and finding post-publication corrections or retractions", + "input": "DOI, paper title, or author name", + "output": "Peer comments, flags, and discussion threads attached to the publication", + "opsec": "passive", + "opsecNote": "Queries PubPeer's public database; searches are not disclosed to paper authors.", + "localInstall": false, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": false, + "invitationOnly": false, + "deprecated": false }, { "name": "Bielefeld Academic Search Engine", "type": "url", - "url": "https://www.base-search.net/Search/Advanced" + "url": "https://www.base-search.net/Search/Advanced", + "description": "Academic search engine indexing over 400 million documents from 12,000+ content providers including institutional repositories, open-access journals, and research databases worldwide.", + "status": "live", + "pricing": "free", + "bestFor": "Broad academic literature search across open-access and institutional repositories", + "input": "Author, title, keyword, DOI, or subject", + "output": "Academic papers, theses, and research documents with metadata and links", + "opsec": "passive", + "opsecNote": "Searches BASE's aggregated index; no direct contact with source institutions.", + "localInstall": false, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": true, + "invitationOnly": false, + "deprecated": false }, { "name": "Google Scholar", "type": "url", - "url": "https://scholar.google.com/" + "url": "https://scholar.google.com/", + "description": "Multidisciplinary academic search engine indexing journal articles, theses, books, conference papers, and patents; includes citation counts and related work discovery.", + "status": "live", + "pricing": "free", + "bestFor": "Comprehensive academic literature discovery with citation tracking across all disciplines", + "input": "Author, paper title, keyword, or institution", + "output": "Academic publications with citation counts, links to full text, and related work", + "opsec": "passive", + "opsecNote": "Searches are logged by Google; results reflect Google's index with no direct contact to journals or authors.", + "localInstall": false, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": false, + "invitationOnly": false, + "deprecated": false }, { "name": "PubMed - National Center for Biotechnology Information", "type": "url", - "url": "https://pubmed.ncbi.nlm.nih.gov/" + "url": "https://pubmed.ncbi.nlm.nih.gov/", + "description": "Free biomedical and life sciences literature database maintained by the NCBI with over 40 million citations; includes abstracts and links to full-text articles.", + "status": "live", + "pricing": "free", + "bestFor": "Biomedical, clinical, and life sciences literature research with high-quality metadata", + "input": "Author, MeSH term, keyword, PMID, or DOI", + "output": "Citation records with abstracts, MeSH terms, and links to full-text sources", + "opsec": "passive", + "opsecNote": "Searches are routed through NCBI servers; queries are subject to NCBI's usage policies.", + "localInstall": false, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": true, + "invitationOnly": false, + "deprecated": false }, { "name": "Open Library", "type": "url", - "url": "https://openlibrary.org/" + "url": "https://openlibrary.org/", + "description": "Internet Archive's open catalog of over 3 million books with borrowable digital editions; provides bibliographic data and full-text access for many out-of-print titles.", + "status": "live", + "pricing": "free", + "bestFor": "Finding and borrowing digitized books, especially out-of-print or historical publications", + "input": "Title, author, ISBN, or subject", + "output": "Book records with metadata, cover images, and links to borrowable or readable editions", + "opsec": "passive", + "opsecNote": "Public searches require no account; borrowing requires free registration which logs activity.", + "localInstall": false, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": true, + "invitationOnly": false, + "deprecated": false }, { "name": "JURN", "type": "url", - "url": "https://www.jurn.org/" + "url": "https://www.jurn.org/", + "description": "Multidisciplinary search engine indexing freely accessible academic articles; covers arts, humanities, ecology, and social sciences with a focus on open-access content.", + "status": "live", + "pricing": "free", + "bestFor": "Open-access academic article discovery in arts, humanities, and social sciences", + "input": "Keyword, author, or subject", + "output": "Links to freely accessible academic articles across indexed journals", + "opsec": "passive", + "opsecNote": "Searches via JURN's Google Custom Search integration; queries are processed by Google.", + "localInstall": false, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": false, + "invitationOnly": false, + "deprecated": false }, { "name": "UK National Archives", "type": "url", - "url": "https://discovery.nationalarchives.gov.uk/" + "url": "https://discovery.nationalarchives.gov.uk/", + "description": "Official online catalog for the UK National Archives providing access to over 32 million records spanning 1,000 years of UK government, legal, and historical documents.", + "status": "live", + "pricing": "free", + "bestFor": "UK historical records, government documents, and legal archives research", + "input": "Person name, place, date, or record reference", + "output": "Archive catalog entries with descriptions, dates, and ordering information for physical or digital access", + "opsec": "passive", + "opsecNote": "Searches the public catalog; no account required for browsing though some documents require in-person access.", + "localInstall": false, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": false, + "invitationOnly": false, + "deprecated": false }, { "name": "OpenGrey EU Papers", "type": "url", - "url": "https://opengrey.eu/" + "url": "https://opengrey.eu/", + "description": "Former European grey literature database maintained by INIST-CNRS that indexed non-conventional scientific and technical documents; archived in 2020 and no longer updated.", + "status": "live", + "pricing": "free", + "bestFor": "Historical European grey literature and non-conventional scientific documents (pre-2020)", + "input": "Keyword, author, or subject", + "output": "Grey literature records including reports, theses, and technical documents", + "opsec": "passive", + "opsecNote": "Static archive; no active data collection occurs during searches.", + "localInstall": false, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": false, + "invitationOnly": false, + "deprecated": true }, { "name": "US Gov Publishing Office - FDsys", "type": "url", - "url": "https://www.gpo.gov/fdsys/" + "url": "https://www.gpo.gov/fdsys/", + "description": "Legacy US Government Publishing Office document system (FDsys) that has been superseded by GovInfo (govinfo.gov); the URL now redirects to the modernized GovInfo platform.", + "status": "live", + "pricing": "free", + "bestFor": "US federal government publications, congressional records, and regulatory documents (use GovInfo instead)", + "input": "Document title, agency, or collection name", + "output": "US government publications in PDF, XML, and other formats", + "opsec": "passive", + "opsecNote": "Government-operated service; searches are logged per federal government policies.", + "localInstall": false, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": false, + "invitationOnly": false, + "deprecated": true }, { "name": "OpenDOAR", "type": "url", - "url": "https://www.opendoar.org/search.php" + "url": "https://www.opendoar.org/search.php", + "description": "Global directory of open-access repositories with over 6,000 academic repositories from 130+ countries; useful for locating institutional repositories and discipline-specific archives.", + "status": "live", + "pricing": "free", + "bestFor": "Finding open-access repositories by institution, country, or subject discipline", + "input": "Institution name, country, or subject area", + "output": "List of matching open-access repositories with metadata and direct links", + "opsec": "passive", + "opsecNote": "Searches OpenDOAR's directory; no direct contact with listed repositories.", + "localInstall": false, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": false, + "invitationOnly": false, + "deprecated": false }, { "name": "Microsoft Academic", "type": "url", - "url": "https://academic.microsoft.com/" + "url": "https://academic.microsoft.com/", + "description": "Microsoft's academic search service indexing hundreds of millions of research papers; note that the original Microsoft Academic service was discontinued in December 2021 and this URL may redirect.", + "status": "live", + "pricing": "free", + "bestFor": "Academic paper discovery with author disambiguation and citation graph analysis", + "input": "Author, title, keyword, or institution", + "output": "Research paper records with metadata, citations, and author profiles", + "opsec": "passive", + "opsecNote": "Searches are processed by Microsoft servers; activity may be subject to Microsoft's privacy policy.", + "localInstall": false, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": false, + "invitationOnly": false, + "deprecated": false }, { "name": "Science Direct", "type": "url", - "url": "https://www.sciencedirect.com/" + "url": "https://www.sciencedirect.com/", + "description": "Elsevier's platform for peer-reviewed scientific literature with access to over 2,900 journals and 30,000 e-books; freely searchable with full-text access requiring subscription or institutional access.", + "status": "live", + "pricing": "freemium", + "bestFor": "Scientific and technical literature search across Elsevier's extensive journal catalog", + "input": "Author, title, keyword, DOI, or journal name", + "output": "Article records with abstracts; full text requires subscription or per-article purchase", + "opsec": "passive", + "opsecNote": "Searches are logged by Elsevier; institutional access requires login which creates an activity record.", + "localInstall": false, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": false, + "invitationOnly": false, + "deprecated": false }, { "name": "Think Tank Search", "type": "url", - "url": "https://guides.library.harvard.edu/hks/think_tank_search" + "url": "https://guides.library.harvard.edu/hks/think_tank_search", + "description": "Harvard Kennedy School Library guide for searching think tank research and policy reports; the referenced Think Tank Search service was deprecated in February 2025.", + "status": "live", + "pricing": "free", + "bestFor": "Policy research and think tank report discovery (see Policy Commons as current alternative)", + "input": "Topic, organization, or keyword", + "output": "Links to think tank research guides and policy report databases", + "opsec": "passive", + "opsecNote": "Accesses a public library guide page; no tracking beyond standard web server logs.", + "localInstall": false, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": false, + "invitationOnly": false, + "deprecated": true }, { "name": "Library Databases", "type": "url", - "url": "https://guides.uflib.ufl.edu/az.php" + "url": "https://guides.uflib.ufl.edu/az.php", + "description": "University of Florida Library's A-Z database directory providing access to hundreds of academic databases covering all disciplines; useful as a reference for locating specialized research databases.", + "status": "live", + "pricing": "free", + "bestFor": "Identifying specialized academic databases by subject for deep literature research", + "input": "Subject area or database name", + "output": "List of academic databases with descriptions and access links", + "opsec": "passive", + "opsecNote": "Public library guide; no account required for browsing the directory.", + "localInstall": false, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": false, + "invitationOnly": false, + "deprecated": false }, { "name": "Copyscape Plagiarism Checker", "type": "url", - "url": "https://www.copyscape.com/" + "url": "https://www.copyscape.com/", + "description": "Online plagiarism detection service that searches the web for copies of submitted text or URLs; useful for verifying content originality or tracing where text has been republished.", + "status": "live", + "pricing": "freemium", + "bestFor": "Detecting plagiarism and tracing where specific text or content has been copied or republished online", + "input": "URL or pasted text", + "output": "List of web pages containing matching or similar text with percentage match scores", + "opsec": "passive", + "opsecNote": "Searches are processed by Copyscape's servers; submitted text is sent to Copyscape for comparison.", + "localInstall": false, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": true, + "invitationOnly": false, + "deprecated": false }, { "name": "Lazy Scholar (T)", "type": "url", - "url": "https://lazyscholar.org/" + "url": "https://lazyscholar.org/", + "description": "Browser extension that automatically finds free legal full-text versions of academic papers when viewing paywalled content; checks open-access repositories and PubMed Central.", + "status": "live", + "pricing": "free", + "bestFor": "Finding free full-text access to paywalled academic papers without institutional subscription", + "input": "Paywalled journal article URL or DOI (via browser extension)", + "output": "Links to free legal full-text versions of the paper from open-access sources", + "opsec": "passive", + "opsecNote": "Extension queries open-access databases in the background; no personal data sent to external servers.", + "localInstall": true, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": false, + "invitationOnly": false, + "deprecated": false }, { "name": "Open Access Scholarly Journals", "type": "url", - "url": "https://www.pagepress.org/" + "url": "https://www.pagepress.org/", + "description": "PAGEPress open-access publisher hosting peer-reviewed journals across biomedical, natural, and social sciences; provides free access to published research articles.", + "status": "live", + "pricing": "free", + "bestFor": "Accessing open-access peer-reviewed research in biomedical and natural sciences", + "input": "Article title, author, or journal name", + "output": "Freely accessible full-text research articles in PDF and HTML formats", + "opsec": "passive", + "opsecNote": "Publicly accessible journal platform; no account required to read articles.", + "localInstall": false, + "googleDork": false, + "registration": false, + "editUrl": false, + "api": false, + "invitationOnly": false, + "deprecated": false }, { "name": "The Open Syllabus Project",