Reviews local branch changes for bugs, security vulnerabilities, and code quality issues, producing a prioritized report with severity ratings and concrete fixes.
Evidence: Why this is real (not already fixed, no existing test, etc.)
Fix: Concrete suggestion
References: OWASP, RFCs, or other standards if applicable
If you find nothing significant, say so - don't invent issues.
Do not make changes - just report findings. I'll decide what to address.
1---2name: find-bugs3description: Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.4risk: unknown5source: community6---78# Find Bugs910Review changes on this branch for bugs, security vulnerabilities, and code quality issues.1112## Phase 1: Complete Input Gathering13141. Get the FULL diff: `git diff $(gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name')...HEAD`152. If output is truncated, read each changed file individually until you have seen every changed line163. List all files modified in this branch before proceeding1718## Phase 2: Attack Surface Mapping1920For each changed file, identify and list:2122* All user inputs (request params, headers, body, URL components)23* All database queries24* All authentication/authorization checks25* All session/state operations26* All external calls27* All cryptographic operations2829## Phase 3: Security Checklist (check EVERY item for EVERY file)3031* [ ] **Injection**: SQL, command, template, header injection32* [ ] **XSS**: All outputs in templates properly escaped?33* [ ] **Authentication**: Auth checks on all protected operations?34* [ ] **Authorization/IDOR**: Access control verified, not just auth?35* [ ] **CSRF**: State-changing operations protected?36* [ ] **Race conditions**: TOCTOU in any read-then-write patterns?37* [ ] **Session**: Fixation, expiration, secure flags?38* [ ] **Cryptography**: Secure random, proper algorithms, no secrets in logs?39* [ ] **Information disclosure**: Error messages, logs, timing attacks?40* [ ] **DoS**: Unbounded operations, missing rate limits, resource exhaustion?41* [ ] **Business logic**: Edge cases, state machine violations, numeric overflow?4243## Phase 4: Verification4445For each potential issue:4647* Check if it's already handled elsewhere in the changed code48* Search for existing tests covering the scenario49* Read surrounding context to verify the issue is real5051## Phase 5: Pre-Conclusion Audit5253Before finalizing, you MUST:54551. List every file you reviewed and confirm you read it completely562. List every checklist item and note whether you found issues or confirmed it's clean573. List any areas you could NOT fully verify and why584. Only then provide your final findings5960## Output Format6162**Prioritize**: security vulnerabilities > bugs > code quality6364**Skip**: stylistic/formatting issues6566For each issue:6768* **File:Line** - Brief description69* **Severity**: Critical/High/Medium/Low70* **Problem**: What's wrong71* **Evidence**: Why this is real (not already fixed, no existing test, etc.)72* **Fix**: Concrete suggestion73* **References**: OWASP, RFCs, or other standards if applicable7475If you find nothing significant, say so - don't invent issues.7677Do not make changes - just report findings. I'll decide what to address.
Run npx skillmds@latest add lucaspmarie-a11y/find-bugs in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Reviews local branch changes for bugs, security vulnerabilities, and code quality issues, producing a prioritized report with severity ratings and concrete fixes. It is listed under Security, Coding & Dev Tools, Code Review, Vulnerability Scanning on SkillMD.
SkillMD's automated safety review verdict for this skill is PASS. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
lucaspmarie-a11y (@lucaspmarie-a11y) published this skill. Their other Agent Skills are listed on their SkillMD profile.