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.
security-review- Author
- Sentry
- 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-reviewruns Claude Code's built-in command, not this skill. - Codex:
$security-review. - Cursor: type
/in the Agent chat and picksecurity-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.
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.
AnyModel