Agent SDK0.2.29

Appearance

Review pull requests for exploitable bugs ​

This agent reads a pull request diff and posts one review comment. It reports exploitable bugs: injection, authz bypass, secret leaks, SSRF, RCE. Style nits stay out.

This template is one model turn: read the diff, then post one comment.

Scaffold ​

text
agent-sdk init ./security-reviewer --template security-reviewer \
  --var repos=acme/api

--var repos must name a repository already connected in Cursor for your account. Separate multiple repositories with commas; they must share one owner. init writes the list to bot/lib/repos.ts.

Connect GitHub through Cursor ​

Connect GitHub in Cursor for those repositories (Settings or cursor.com/dashboard). Sign the host in:

text
cd security-reviewer
agent-sdk login

cursorAccount pulls SCM events from Cursor and mints a short-lived, repo-scoped credential. ctx.host.github and child gh commands share it. See the GitHub guide.

First review ​

text
agent-sdk dev

dev starts the Cursor event relay for the watched repos. To drive a known PR without waiting on a live push:

text
agent-sdk github replay https://github.com/acme/api/pull/12 --dir .

replay needs pull access. Draft PRs and repos outside bot/lib/repos.ts are ignored. The channel writes pr/diff.patch after the wake is acknowledged, then starts a model turn. The model calls post_findings once.

Chat replies stay in the playground. post_findings writes the GitHub comment.

What to edit ​

  • bot/lib/repos.ts: watched repos
  • bot/instructions.md: what counts as a finding and the comment shape
  • evals/review.eval.ts: smoke cases

Evals ​

Use the two smoke cases, one XSS fixture and one docs-only change, as a local exercise:

text
agent-sdk eval

Eval sessions skip the GitHub write.

Deploy ​

text
agent-sdk deploy

Run it from the agent's git checkout. The command infers repository, ref, path, and slug. The deployment uses the team's Cursor GitHub connection for the same watched repos.