Security Guidance
Security scan passedAnthropic's security review for Claude Code: flags injection, XSS, secrets and more as Claude edits, finishes a turn and commits.

SpecterOps' security review for Go: your agent audits auth, injection, SSRF, files, crypto, concurrency and cgo, then writes a report.
by specterops· SecurityUnclaimed · Yours? Claim it
4 images
About
Go Review is SpecterOps' Claude Code plugin for security reviews of Go code: libraries, frameworks, CLIs, HTTP and gRPC services, and backend applications. Its skill builds an inventory of the code with Go's own parser, picks the review areas that apply, hands each one to a worker, then runs judges that merge duplicates and weed out false positives before it writes a report. What it reviews - Authentication and authorization boundaries - Request parsing and body limits - Outbound HTTP and SSRF - SQL and storage access, and command execution - Template rendering and XSS - Filesystem access and archive extraction - JWT, TLS, cookie and session handling - Goroutines, timeouts, cancellation and shared state - unsafe and cgo boundaries How you use it Run /go-review:go-review. It asks for a threat model (remote, local unprivileged or both), a severity filter (all, medium or high) and, if you like, a folder to limit the review to. Findings go to .go-review-results/<timestamp>/ in your project, with a REPORT.md and a REPORT.sarif. How to install it In Claude Code, run /plugin marketplace add SpecterOps/skills, then /plugin install go-review@specterops-skills. SpecterOps also supports it in Codex. Good to know - It needs Go 1.22 or newer and Python 3.11 or newer. It uses your installed Go toolchain and doesn't download tools or fetch your modules. - Its inventory reads Go syntax rather than types, so a finding is reported only after its data flow is checked for reachability. - The results folder can hold source excerpts, unconfirmed findings and local paths, so review it before you commit or share it. - Its workers use the model you're already using.
Plugins people install alongside Go Review.
Once it’s added
“Run a security review of this Go service”
“Check that every route and interceptor in our Go API enforces authorization”
“Review this gRPC gateway for SSRF and injection”
“Check this Go CLI for unsafe file and archive handling”
“Look for goroutine leaks and missing timeouts in this daemon”
“Review the unsafe and cgo code in this package”
Before you add it
Reads only
Your Go source, within the folder you choose · Its imports, routes, calls and goroutines, through an inventory built with Go's parser
Makes changes · your agent can ask first
A results folder in your project (.go-review-results) with findings, a Markdown report and a SARIF report
From people who use it
Step by step
Nothing new reaches your agent until a person has looked at it.
Scanned on every change, and again when our rules improve.
Runs on your machine.
Runs on your machine.
/plugin marketplace add SpecterOps/skills /plugin install go-review@specterops-skills
Scanned and passed · checked 6 h ago
No reviews yet. Used Go Review? Say how it went.
Write a reviewNobody has shared how they use Go Review yet.
Security scan
Passed
Safe to install in every agent it supports. Claude plugins.
Plugins people install alongside Go Review.
Anthropic's security review for Claude Code: flags injection, XSS, secrets and more as Claude edits, finishes a turn and commits.
Equips your coding agent with SAST, dependency scanning, a phased hardening workflow and STRIDE threat-modeling skills.
Alireza Rezvani's Claude Code hook that stops Claude before it writes common security anti-patterns, such as eval, pickle or SQL f-strings.
Microsoft's skills for Azure Data Explorer: build Kusto graphs, compose IRQL threat hunts and turn results into visual graphs.