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.4license: Apache-2.05source: "https://github.com/getsentry/skills"6attribution: "getsentry/skills by Sentry"7version: "1.0.0"8metadata:9 source: https://skillmd.com/skills/mouadja02/find-bugs10---1112> **Attribution:** Sourced from [getsentry/skills](https://github.com/getsentry/skills) by [Sentry](https://sentry.io), licensed Apache-2.0. Modified for this collection.1314# Find Bugs1516Review changes on this branch for bugs, security vulnerabilities, and code quality issues.1718## Phase 1: Complete Input Gathering19201. Get the FULL diff: `git diff $(gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name')...HEAD`212. If output is truncated, read each changed file individually until you have seen every changed line223. List all files modified in this branch before proceeding2324## Phase 2: Attack Surface Mapping2526For each changed file, identify and list:2728* All user inputs (request params, headers, body, URL components)29* All database queries30* All authentication/authorization checks31* All session/state operations32* All external calls33* All cryptographic operations3435## Phase 3: Security Checklist (check EVERY item for EVERY file)3637* [ ] **Injection**: SQL, command, template, header injection38* [ ] **XSS**: All outputs in templates properly escaped?39* [ ] **Authentication**: Auth checks on all protected operations?40* [ ] **Authorization/IDOR**: Access control verified, not just auth?41* [ ] **CSRF**: State-changing operations protected?42* [ ] **Race conditions**: TOCTOU in any read-then-write patterns?43* [ ] **Session**: Fixation, expiration, secure flags?44* [ ] **Cryptography**: Secure random, proper algorithms, no secrets in logs?45* [ ] **Information disclosure**: Error messages, logs, timing attacks?46* [ ] **DoS**: Unbounded operations, missing rate limits, resource exhaustion?47* [ ] **Business logic**: Edge cases, state machine violations, numeric overflow?4849## Phase 4: Verification5051For each potential issue:5253* Check if it's already handled elsewhere in the changed code54* Search for existing tests covering the scenario55* Read surrounding context to verify the issue is real5657## Phase 5: Pre-Conclusion Audit5859Before finalizing, you MUST:60611. List every file you reviewed and confirm you read it completely622. List every checklist item and note whether you found issues or confirmed it's clean633. List any areas you could NOT fully verify and why644. Only then provide your final findings6566## Output Format6768**Prioritize**: security vulnerabilities > bugs > code quality6970**Skip**: stylistic/formatting issues7172For each issue:7374* **File:Line** - Brief description75* **Severity**: Critical/High/Medium/Low76* **Problem**: What's wrong77* **Evidence**: Why this is real (not already fixed, no existing test, etc.)78* **Fix**: Concrete suggestion79* **References**: OWASP, RFCs, or other standards if applicable8081If you find nothing significant, say so - don't invent issues.8283Do not make changes - just report findings. I'll decide what to address.
Run npx get-skill add mouadja02/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. 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. This skill is licensed under Apache-2.
mouadja02 (@mouadja02) published this skill. Their other Agent Skills are listed on their SkillMD profile.