review-pr

$npx mdskill add trailofbits/skills/review-pr

Review the branch's change surface, not the whole repository.

SKILL.md

.github/skills/review-prView on GitHub ↗
---
name: review-pr
description: "Reviews the current branch's changes against its base branch as a pull request: correctness of new and modified code, test coverage for it, and documentation accuracy. Use when asked to review a branch, a diff, or a pull request."
allowed-tools: Read Grep Glob Bash
---

# PR Review

Review the branch's change surface, not the whole repository.

1. Establish the diff: `git diff <base>...HEAD` (and `git diff <base>` when the working
   tree carries uncommitted changes that belong to the branch). The base branch is named
   by the caller; fall back to `main`.
2. Review every changed hunk for correctness: wrong results on edge inputs, unhandled
   error paths, and behavior that contradicts the function's name or callers.
3. Check test coverage for the changed behavior: new logic without a test exercising its
   edge cases is a finding.
4. Check documentation the diff made stale: statements in README or docs that were true
   on the base branch and are false after the change.
5. Report every defect found, each with a severity; include minor and informational
   findings. Do not report defects in files the branch did not touch — they are outside
   the pull request.

More from trailofbits/skills

SkillDescription
address-sanitizerBuilds and runs code under AddressSanitizer to catch buffer overflows, use-after-free, and other memory errors during fuzzing or tests. Covers -fsanitize=address builds, ASAN_OPTIONS, reading the crash report, LeakSanitizer, and the overhead and platform trade-offs. Use when fuzzing C/C++ or Rust that has unsafe blocks or FFI, when debugging a memory corruption crash, or when reading an ASan stack trace.
adjudicate-regressionUse when deciding whether source and live reproduction evidence establish a new regression or an exclusion.
aflppSets up and runs AFL++ for multi-core fuzzing of C/C++ projects built with afl-clang-fast or afl-gcc-fast. Covers instrumentation modes, parallel main and secondary campaigns, persistent mode, corpus minimization, and crash triage. Use when scaling fuzzing across cores, fuzzing a mature C/C++ codebase, reading the afl-fuzz status screen, or moving on after libFuzzer has plateaued.
agentic-actions-auditorAudits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations.
algorand-vulnerability-scannerScans Algorand smart contracts for 11 common vulnerabilities including rekeying attacks, unchecked transaction fees, missing field validations, and access control issues. Use when auditing Algorand projects (TEAL/PyTeal).
atherisSets up and runs Atheris, the coverage-guided Python fuzzer built on libFuzzer. Covers TestOneInput harnesses, FuzzedDataProvider, instrumenting both pure Python and native C extensions, and running under AddressSanitizer. Use when fuzzing a Python package, hunting memory corruption in a Python C extension, or choosing between Atheris and Hypothesis for a Python target.
audit-augmentation>
audit-context-buildingUnderstand a codebase before looking for bugs in it - what each function assumes, what it guarantees, and what it depends on elsewhere. Use when starting an audit, threat model, or architecture review on unfamiliar code, and before any vulnerability-hunting pass.
audit-prep-assistantPrepares codebases for security review using Trail of Bits' checklist. Helps set review goals, runs static analysis tools, increases test coverage, removes dead code, ensures accessibility, and generates documentation (flowcharts, user stories, inline comments). Use when preparing your own codebase to be audited by someone else, getting a repository review-ready before an external security review, deciding what to fix before auditors start, or asking what assessors need from a project. For understanding unfamiliar code you are about to audit, use audit-context-building instead.
burpsuite-project-parserSearches and explores Burp Suite project files (.burp) from the command line. Use when searching response headers or bodies with regex patterns, extracting security audit findings, dumping proxy history or site map data, or analyzing HTTP traffic captured in a Burp project.