leaklens
Catch data leakage in your datasets AND ML code before it fools you
What XERJ indexed
Snapshot
The whole repository at commit c5f1d8bc85 (2026-10-22). main is 20 commits ahead.
Selected work
“dataflow tracking, chained-call detection, SARIF output; benchm…”. 11 files, 330 lines in leaklens, examples, tests.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-24. Same terms as the repository. Answers name the repo, the commit and the file:line.
selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution
data-leakagedata-sciencefastapigithub-actionmachine-learningmlflowmlopsscikit-learn
Example questions
- How does leaklens implement data-leakage?
- What does leaklens do in leaklens?
- Show the data-science code in leaklens.
Inside the indexed corpus
- Languages by size: Python 99.8%, Dockerfile 0.2%.
- On GitHub since 2026-10-20, last push 2026-10-29, 52 commits on main.
- The pin is 20 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for eyadstein/leaklens on 2026-10-29, and the LICENSE file at commit c5f1d8bc85 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Eyad Ahmed (@eyadstein) has 1 selected repository on the hub.
Using XERJ with leaklens
- RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
- Best MCP servers for local code search in 2026, compared
- Best grep alternative for AI coding agents (2026)
- Ask questions about a GitHub repo without cloning it
The prompt
Paste it into your AI agent. It clones eyadstein/leaklens at the pinned commit and indexes it on your machine.
Search the GitHub repository eyadstein/leaklens with XERJ (https://hub.xerj.org/corpus/eyadstein--leaklens). Run these in a shell, in order, and check each result before the next: 1. xerj --help (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh 2. git clone https://github.com/eyadstein/leaklens leaklens && git -C leaklens checkout c5f1d8bc85f36263caff3e1f4c4a25bc7af68e6d 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./leaklens --url http://127.0.0.1:9200 --prefix leaklens --progress plain 5. xerj autoindex map --url http://127.0.0.1:9200 Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt Licence: MIT. Keep the copyright notice and credit the authors.
Related
Eyad Ahmed AI, prompts and agents corporacognitagiskardadalflowoffbeatash/Netflix-movie-recommendation-engineTanishBane/wastewise-aiiamvisheshsrivastava/insightdesk-ai
Stats: GitHub API, fetched 2026-10-29. Selected work and consent: the XERJ registry.