Review a PR, or a PR linked to an issue, for security risks. Check nine categories and report PASS, WARNING, or FAIL. Use when reviewing code for vulnerabilities, secrets, injection, authorization bypasses, or unsafe configuration. Trigger keywords - security review, code review, appsec, vulnerability assessment, security audit, review PR security.
npx skills add https://github.com/NVIDIA/NemoClaw --skill nemoclaw-maintainer-security-code-review
<!-- SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. -->
<!-- SPDX-License-Identifier: Apache-2.0 -->
Review the changes in a GitHub PR for security. An issue input must identify one open linked PR.
Report a verdict for each category.
gh (GitHub CLI) must be installed and authenticated.git must be available.If the user gives a PR or issue URL, extract the owner, repository, and number.
Otherwise, ask for the URL.
Supported URL formats:
https://github.com/OWNER/REPO/pull/NUMBERhttps://github.com/OWNER/REPO/issues/NUMBERFor a PR URL, verify the number before Step 2:
gh pr view <number> --repo OWNER/REPO --json number,url
For an issue URL, list its open closing PRs:
gh issue view <number> --repo OWNER/REPO --json closedByPullRequestsReferences \
--jq '.closedByPullRequestsReferences | map(select(.state == "OPEN")) | .[].number'
Continue only when this returns one PR number, and verify that number with gh pr view.
If it returns zero or more than one, stop and ask for the PR URL.
Use the verified PR number in each later command.
Compare gh repo view --json nameWithOwner -q .nameWithOwner with the URL.
If the repositories match, check out the verified PR:
gh pr checkout <number>
If the repositories do not match, clone the target to a temporary directory:
REVIEW_DIR=$(mktemp -d)
gh repo clone OWNER/REPO "$REVIEW_DIR"
cd "$REVIEW_DIR"
gh pr checkout <number>
List all files changed from the base branch:
git diff main...HEAD --name-status
If the PR targets another branch, use that branch as the base. Check it with:
gh pr view <number> --json baseRefName -q .baseRefName
Read each changed file. Read its diff:
git diff main...HEAD -- <file>
If a PR changes more than 30 files, review them in this order:
For each of the nine categories, assign a verdict:
.env files, PEM/key files, credential JSON).pickle.loads, yaml.unsafe_load, eval, new Function, or similar).Structure the output as follows:
One paragraph summarizing the risk and whether the PR is safe to merge.
One row per finding:
| # | Category | Severity | File:Line | Description | Recommendation |
|---|----------|----------|-----------|-------------|----------------|
If there are no findings, state that the review found none.
For each category, give its PASS, WARNING, or FAIL verdict and reason.
List every file analyzed.
Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.
Expert in secure mobile coding practices specializing in input validation, WebView security, and mobile-specific security patterns. Use PROACTIVELY for mobile security implementations or mobile security code reviews.
Expert in secure frontend coding practices specializing in XSS prevention, output sanitization, and client-side security patterns. Use PROACTIVELY for frontend security implementations or client-side security code reviews.
Security hardening reviewer for GitHub Actions workflow files (.github/workflows/*.yml). Reasons about the Actions threat model that pattern matchers and general code linters miss — untrusted-input script injection, privileged triggers running fork code, mutable action references, and over-scoped tokens. Use this skill when asked to review, audit, harden, or secure a GitHub Actions workflow, when writing a new workflow, or for any request like "is this workflow safe?", "review my CI for security issues", "why is pull_request_target dangerous here?", "pin my actions", or "lock down GITHUB_TOKEN permissions". Covers script injection via ${{ }} interpolation, pull_request_target / workflow_run privilege escalation, SHA-pinning of third-party actions, least-privilege permissions, GITHUB_ENV/GITHUB_OUTPUT injection, secret exposure, OIDC over long-lived credentials, and self-hosted runner exposure on public repositories.
>- Run Semgrep static analysis scan on a codebase using parallel subagents. Supports two scan modes — "run all" (full ruleset coverage) and "important only" (high-confidence security vulnerabilities). Automatically detects and uses Semgrep Pro for cross-file taint analysis when available. Use when asked to scan code for vulnerabilities, run a security audit with Semgrep, find bugs, or perform static analysis. Spawns parallel workers for multi-language codebases.
Expands one confirmed or suspected vulnerability into a Trailmark graph neighborhood of variant candidates by finding sibling functions, shared callers and callees, common sensitive sinks, common entrypoint paths, interface implementations, override relationships, type/reference neighbors, and structurally similar nodes. Use after one issue is found to seed variant-analysis, semgrep-rule-creator, static-analysis, or manual review with graph-derived candidate locations.
Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities". Do NOT use for accessibility (use web-accessibility), SEO (use seo), performance (use core-web-vitals), or comprehensive multi-area audits (use web-quality-audit).
Use when the user asks for a deep, exhaustive, multi-pass, or variance-reducing repository-wide or scoped-path Codex Security scan. Run repeated independent discovery passes over one resolved scope with worker-specific threat models, semantically merge candidates, synthesize one canonical validation threat model, then run validation, attack-path analysis, canonical JSON completion, and generated reporting once. Do not use for PRs, commits, branch diffs, or working-tree diffs.
Take nvidia/nemoclaw-maintainer-security-code-review from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.