pr-privacy

pr-privacy is an Application security skill for AI agents, published by cardstack in the boxel repository on GitHub. Skillspace rates pr-privacy F (54/100) and it passed the safety scan; the rating is based on static analysis only.

Redact user data before publishing anything to GitHub. This repo is open source, so PR titles, PR descriptions, PR review comments, PR review replies, issue comments on PRs, commit messages, source-code strings, code comments, test fixtures, snapshot files, and any other committed file content are all public forever and indexed by search engines. Use this skill whenever you are about to call `gh pr create`, `gh pr comment`, `gh pr review`, `gh issue comment`, or any `mcp__github__*` tool that posts content (create_pull_request, add_comment_to_pending_review, add_issue_comment, pull_request_review_write, update_pull_request, etc.); whenever you are about to write a commit message; and whenever you are about to `git add` / `git commit` source code, code comments, fixtures, or snapshot files that quote data observed from production or staging — CloudWatch logs, the boxel_index database, EFS filesystem listings, realm metadata, Matrix room state, or a user's browser. Linear (tickets,…

Grade

F

Quality

54 / 100

Safety

Passed

GitHub stars

23

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.