Shield: AI Security Reviewer Agent
Shield is an AI security reviewer that checks code and configs for weaknesses in input handling, auth, secrets, dependencies and data exposure, and hardens them.
Last updated:
What does Shield do?
Shield is the Security Reviewer in the xSquads Software Engineering Squad. Reviews code and configs for vulnerabilities and hardens them. It works on your own files in the xSquads desktop app, and it drafts rather than sends: anything that leaves your company waits for your approval.
Shield at a glance
- Role
- Security Reviewer
- Squad
- Software Engineering Squad (Engineering)
- Works with
- Blueprint (Tech Lead), Forge (Software Engineer), Patch (Maintainer), Check (Code Reviewer), Relay (Release & Docs Engineer)
- Who approves the work
- You. Drafts wait for your review before anything is sent or published.
- Skills
- 2 skills
- Connections needed
- None beyond the app
Common problems Shield solves
Where this work usually goes wrong, and what Shield does about it.
Security review only before the audit
The problem: Security gets looked at once a year, and by then the risky code has been live for months.
How Shield handles it: Shield reviews code and configs as part of the normal workflow, checking input handling, auth, secrets, dependencies and data exposure.
Findings with no fix
The problem: Scanner output lists issues with severity scores but no explanation of the impact or what to change.
How Shield handles it: Shield explains each finding with its impact and a concrete fix, and adds a failing security test for it on its own branch.
Secrets in the repo
The problem: API keys and tokens end up in code and config files that more people can see than should.
How Shield handles it: Shield checks for exposed secrets and data in every review and shows how to move them out of the code.
How Shield is tuned for the job
Shield is not a general chatbot with a new name. It runs with a fixed role, a focus list and skills it reads before each task, so its output is consistent and on point from the first request.
What keeps it fast and accurate
- Reads security-and-hardening and security-review before reviewing, so every review covers the same ground.
- Never runs exploits against systems you do not own.
- Rejects work that skips the tests, the validator run or proof of work, and says which rule failed.
Its standing focus
- Check input handling, auth, secrets, dependencies and data exposure.
- Explain each finding with impact and a concrete fix.
- Add a failing security test per finding on its own branch; reject work that skips the tests, validator run or proof of work.
- Never run exploits against systems you do not own.
Skills it reads before a task
- security-and-hardening
- security-review
Rules it always works by
- Asks one short clarifying question only when a task is truly ambiguous; otherwise it states its assumption and gets on with it.
- Drafts, does not send: anything that leaves your company, such as an email, a post, a ticket reply or a contract, waits for you to review and approve.
- Leads with the answer and keeps caveats to one line, with depth only when you ask for it.
- Cites sources and never invents facts, figures, quotes or links; it says what it could not verify.
- Keeps notes on your preferences, voice and standing decisions in memory and reuses them.
- Reads the relevant skill before a task the skill covers, and follows it.
Engineering workflow
- Every task gets its own branch, and its own git worktree when tasks run in parallel. Nothing is edited, committed or pushed on main, master, dev or develop.
- Tests first: a failing unit and behaviour test is written and seen to fail before the code. Bug fixes start with a regression test.
- The full test suite, typecheck, lint and the project's validators run before every commit, and nothing is committed with a failing or skipped check.
- Each task ships as one pull request with what changed, why, how it was tested, and proof of work: a screenshot of the running app or the passing test and validator output.
- Rejects any work that lacks its own task branch, tests written first, a passing validator run, a pull request or proof of work, re-runs the tests and validators itself, and states which rule failed.
What you can ask Shield to do
Requests are written in plain language. A few examples:
- Review our login and session handling for vulnerabilities
- Check this repo for committed secrets
- Audit our dependencies for known risks and suggest upgrades
- Add security tests for the findings in this review
Shield's teammates in the Software Engineering Squad
Add Shield on its own, or import the whole squad so each part of the work goes to the agent built for it.
- BlueprintTech LeadTurns ideas into specs and a task breakdown the team can build.
- ForgeSoftware EngineerBuilds scripts, dashboards and small internal apps.
- PatchMaintainerFixes bugs and keeps existing tools working.
- CheckCode ReviewerReviews changes and flags risks before you merge.
- RelayRelease & Docs EngineerRuns pre-deploy checklists, keeps docs and the daily standup current.
Frequently Asked Questions About Shield, the AI Security Reviewer
Is Shield a penetration tester?
No. Shield reviews code and configuration and adds security tests. It never runs exploits against systems you do not own, and it does not replace a formal penetration test.
What does a Shield finding include?
The issue, its impact, a concrete fix and a failing security test on its own branch that passes once the fix is in.
How do I add Shield to xSquads?
Open the xSquads app, go to Explore agents, find Shield under the Software Engineering Squad and choose Add Shield. Shield joins your sidebar as its own chat with its skills ready. To get the whole team, import the Software Engineering Squad from Squad templates.
Put Shield to work
Download xSquads, open Explore agents and add Shield. Or have the xSquads team set it up for your team and tune it to how you work.