Security review, Sentry

Reviews a file, diff or component for exploitable vulnerabilities with OWASP-based references, researches the codebase before flagging and reports only findings reached by attacker-controlled input. Use when a change needs a low-noise security review.

SecurityPack: Sentry skillslinksecurity-review
Author
Source
getsentry/skills/skills/security-review @ a582c51
License
CC BY-SA 4.0

About this skill

What it does

Sentry's security review looks for exploitable vulnerabilities in a file, diff or component and reports only high-confidence ones. It reports on the scope you name but researches the whole codebase first: where the input really comes from, whether it is validated upstream, what the framework and settings already do. A pattern counts only when attacker-controlled input reaches it; with the source unclear it goes under "Needs verification", and theoretical or defence-in-depth issues are dropped. Much of the weight sits in the "do not flag" rules: values from settings, environment variables and config files are server-controlled; Django, React and Vue templates escape by default; ORM and parameterized queries are safe unless string interpolation reaches .raw(), .extra() or RawSQL(); test files and dead code are skipped.

The agent loads references by code type. The author's folder has 17 OWASP-based files in references/ (injection, XSS, auth, crypto, deserialization, SSRF, CSRF, misconfiguration, supply chain and more, down to prototype pollution and prompt injection), language guides for Python and JavaScript, and infrastructure/docker.md. Django access control goes to Django access control review and GitHub Actions to GitHub Actions security review when those are installed. Findings come as VULN-nnn with location, impact, evidence and fix on a four-level scale; with nothing found, the report says so in one sentence.

When to use it, and when not

Use it before merging code that handles requests, uploads, templates, crypto, serialization or outbound calls, best in Python or JavaScript; other languages fall back to the general references.

It runs no scanners or dynamic tests, has no Kubernetes or Terraform guides, and is not a general code review.

How to run it

We do not copy this skill: its references derive from the OWASP Cheat Sheet Series under CC BY-SA 4.0, while the repository is Apache-2.0. Install it from the author's repository; the button on this page leads there. The author's README offers a Claude Code plugin with the whole Sentry set (claude plugin marketplace add getsentry/skills, then claude plugin install sentry-skills@sentry-skills) or npx skills add getsentry/skills for other agents. Invocation:

  • Claude Code with the plugin: /sentry-skills:security-review, or ask for the skill by name. A bare /security-review runs Claude Code's built-in command, not this skill.
  • Codex: $security-review.
  • Cursor: type / in the Agent chat and pick security-review.

Example: /sentry-skills:security-review Review api/uploads.py; trace where the filename comes from before flagging anything.

How it differs from similar skills

Security review from our catalog also traces input to sinks, adds grep commands and puts non-exploitable issues under "hardening suggestions". Both are named security-review, so only one can sit in a skills folder at a time. Security best-practice review from OpenAI also guides writing secure code in Python, JavaScript and Go. For what counts as a finding in a given repository, see SECURITY_MODEL.md for review tools, although this skill does not load such a policy yet. Find bugs in branch changes from the same pack is a lighter pass: an eleven-item security checklist over every changed file of the branch, which also catches ordinary bugs. Security audit for codebases and services and the Claude Security plugin are full audits with subagents, where separate verifiers check every finding.

Install

This skill is not copied to the catalog: its licence allows a copy only under the same licence, and the catalog does not copy under such licences. Install it from the author's repository.

Open the source

Connect through AnyModel API

This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.

More from the pack Sentry skills

AGENTS.md and CLAUDE.md writer

Writes or trims a repository's AGENTS.md to under 60 lines of commands, conventions and pointers to existing docs, checks every path, and makes CLAUDE.md a symlink to it. Use when a repo needs agent instructions or its current file has grown long or stale.

Claude Code settings audit

Detects a repository's stack and proposes a Claude Code settings.json allow list of read-only commands for the tools it actually uses, plus docs domains and Sentry or Linear MCP entries. Use when setting up Claude Code permissions or auditing existing ones.

Code review, Sentry practices

Reviews a change by Sentry's guidelines: runtime errors, performance and N+1 queries, side effects, compatibility, security, design and tests, with a polite tone and approval once only minor issues remain. Use when reviewing a pull request or branch.

Code simplifier

Simplifies recently changed code without changing behaviour: less nesting, no nested ternaries, clearer names, no redundant abstractions, while following CLAUDE.md conventions. Use when code works but reads heavier than it should and needs a cleanup pass.

Conventional commit messages

Commits in Sentry's Conventional Commits style: a feature branch instead of main, a typed capitalised subject up to 70 characters, Fixes or Refs footers, no personal data. Use when asked to commit changes or draft a commit message.

Django access control review

Audits Django and DRF code for IDOR and broken access control by learning the app's authorization model and tracing each endpoint from ID to query, reporting only confirmed gaps with enforcing fixes. Use when reviewing views, viewsets or tenant isolation.

Find bugs in branch changes

Reviews the commits on the current branch for security holes, bugs and quality issues with an eleven-item checklist and reports verified findings with file, line, severity and fix, without editing code. Use when you want a security-first pass before a PR.

GitHub Actions security review

Audits GitHub Actions workflows for attacks an outsider without write access can run: pwn requests, expression injection, comment commands, token theft, poisoned agent configs, unpinned actions. Use when reviewing CI security or changing workflows.

Iterate a PR until CI is green

Drives an open PR to green: fixes failing CI and high and medium review comments, verifies locally, commits, pushes and repeats, stopping at human approval or draft gates. Use when a PR is red or has review feedback to work through.

PR title and description writer

Writes or refreshes a PR title in Sentry's conventional format and a short reviewer-facing description without template headings or test logs, then opens a draft or updates the PR. Use when opening a PR or after commits change its scope.

Prompt optimizer

Writes, repairs or ports system and agent prompts against a small eval set, comparing candidate rewrites on the same cases and checking the winner on held-out ones. Use when a prompt is unreliable, moves to another model family or needs evals.

Secret leaks through serialization

Finds secrets that leak when a credential field on a dataclass, pydantic model or JS object meets code that logs or traces whole objects, searching the whole repository for the other half. Use when a change adds such a field or a wholesale sink.

SECURITY_MODEL.md for review tools

Writes and maintains SECURITY_MODEL.md, telling security review tools a repository's exposure, invariants, reportable finding classes and owner-confirmed exclusions, with a script that flags stale references. Use when preparing a repo for automated review.

Agent skill security scanner

Audits an agent skill before installation: a static scan for prompt injection, hidden Unicode, secrets, risky scripts and structural traps, then a review of intent and permissions ending in a verdict. Use when a skill comes from an outside source.

Skill writer by the Agent Skills spec

Creates and improves agent skills by Sentry's workflow: sources with provenance, the simplest execution shape, SPEC.md and SOURCES.md, precision passes after each change and a structural validator. Use when building a skill that a team will maintain.

Django performance review

Reviews Django and DRF code for N+1 queries, unbounded querysets, missing indexes and write loops, validating table size and hot paths before reporting. Use when a Django view or endpoint is slow or a change touches large tables.