Add intelligent, security-first PR sweeper automation - #483
Merged
soyalejolopez merged 1 commit intoJul 22, 2026
Conversation
A two-stage, pwn-request-safe automation that helps maintainers triage community PRs quickly while keeping untrusted fork code away from secrets. Stage 1 (pull_request_target, no checkout of PR code): deterministic guardrails - size/scope caps, path/secret/binary heuristics, license & DCO checks, and label routing. Never executes PR code. Stage 2 (workflow_run, read-only token): optional AI review summary posted as a sticky comment. Models are configurable (default GitHub Models: gpt-5 + o3, with an Azure OpenAI fallback for Opus-class review); no auto-merge. Includes: CODEOWNERS (placeholder maintainer team, documented), Dependabot for GitHub Actions with SHA-pin awareness, config in .github/pr-sweeper.config.mjs, helper libs under .github/scripts/pr-sweeper/, and a README explaining setup + required secrets. Entirely opt-in and least-privilege by design. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: cecb163d-04c4-4b01-ab7a-14d25f7ec690
Contributor
🛰️ PR Sweeper reportRisk: 🟠 MEDIUM · Security gate: ✅ passing · Files: 10 🔒 Automated guardrails (authoritative)
🤖 Dual-model AI review (advisory)AI review unavailable for this run (models not reachable or no diff). Guardrails above are unaffected.
The automated guardrails are authoritative and gate the security status. The AI review is advisory and never auto-merges. Thanks for contributing to FastTrack! 🛩️ |
github-actions
Bot
added
sweeper:risk-medium
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
A two-stage, pwn-request-safe automation that helps maintainers triage community PRs quickly while keeping untrusted fork code away from secrets.
Stage 1 (pull_request_target, no checkout of PR code): deterministic guardrails
sticky comment. Models are configurable (default GitHub Models: gpt-5 + o3, with
an Azure OpenAI fallback for Opus-class review); no auto-merge.
Includes: CODEOWNERS (placeholder maintainer team, documented), Dependabot for GitHub Actions with SHA-pin awareness, config in .github/pr-sweeper.config.mjs, helper libs under .github/scripts/pr-sweeper/, and a README explaining setup + required secrets. Entirely opt-in and least-privilege by design.
Co-authored-by: Copilot App 223556219+Copilot@users.noreply.github.com
Copilot-Session: cecb163d-04c4-4b01-ab7a-14d25f7ec690