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.
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.4---567# Find Bugs89Review changes on this branch for bugs, security vulnerabilities, and code quality issues.1011## When to Use This Skill1213Use this skill when:14- Asked to review changes15- Finding bugs in code16- Performing security reviews17- Auditing code on the current branch18- Reviewing pull request changes1920## Phase 1: Complete Input Gathering21221. Get the FULL diff: `git diff $(gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name')...HEAD`232. If output is truncated, read each changed file individually until you have seen every changed line243. List all files modified in this branch before proceeding2526## Phase 2: Attack Surface Mapping2728For each changed file, identify and list:2930* All user inputs (request params, headers, body, URL components)31* All database queries32* All authentication/authorization checks33* All session/state operations34* All external calls35* All cryptographic operations3637## Phase 3: Security Checklist (check EVERY item for EVERY file)3839* [ ] **Injection**: SQL, command, template, header injection40* [ ] **XSS**: All outputs in templates properly escaped?41* [ ] **Authentication**: Auth checks on all protected operations?42* [ ] **Authorization/IDOR**: Access control verified, not just auth?43* [ ] **CSRF**: State-changing operations protected?44* [ ] **Race conditions**: TOCTOU in any read-then-write patterns?45* [ ] **Session**: Fixation, expiration, secure flags?46* [ ] **Cryptography**: Secure random, proper algorithms, no secrets in logs?47* [ ] **Information disclosure**: Error messages, logs, timing attacks?48* [ ] **DoS**: Unbounded operations, missing rate limits, resource exhaustion?49* [ ] **Business logic**: Edge cases, state machine violations, numeric overflow?5051## Phase 4: Verification5253For each potential issue:5455* Check if it's already handled elsewhere in the changed code56* Search for existing tests covering the scenario57* Read surrounding context to verify the issue is real5859## Phase 5: Pre-Conclusion Audit6061Before finalizing, you MUST:62631. List every file you reviewed and confirm you read it completely642. List every checklist item and note whether you found issues or confirmed it's clean653. List any areas you could NOT fully verify and why664. Only then provide your final findings6768## Output Format6970**Prioritize**: security vulnerabilities > bugs > code quality7172**Skip**: stylistic/formatting issues7374For each issue:7576* **File:Line** - Brief description77* **Severity**: Critical/High/Medium/Low78* **Problem**: What's wrong79* **Evidence**: Why this is real (not already fixed, no existing test, etc.)80* **Fix**: Concrete suggestion81* **References**: OWASP, RFCs, or other standards if applicable8283If you find nothing significant, say so - don't invent issues.8485Do not make changes - just report findings. I'll decide what to address.
Run npx skillmds@latest add ncdevshiv/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.
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. It is listed under Security on SkillMD.
This skill has not completed SkillMD's automated safety review yet. 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.
ncdevshiv (@ncdevshiv) published this skill. Their other Agent Skills are listed on their SkillMD profile.