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---56# Find Bugs
78Review changes on this branch for bugs, security vulnerabilities, and code quality issues.
910## When to Use This Skill
1112Use this skill when:
13- Asked to review changes
14- Finding bugs in code
15- Performing security reviews
16- Auditing code on the current branch
17- Reviewing pull request changes
1819## Phase 1: Complete Input Gathering
20211. Get the FULL diff: `git diff $(gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name')...HEAD`
222. If output is truncated, read each changed file individually until you have seen every changed line
233. List all files modified in this branch before proceeding
2425## Phase 2: Attack Surface Mapping
2627For each changed file, identify and list:
2829* All user inputs (request params, headers, body, URL components)
30* All database queries
31* All authentication/authorization checks
32* All session/state operations
33* All external calls
34* All cryptographic operations
3536## Phase 3: Security Checklist (check EVERY item for EVERY file)
3738* [ ] **Injection**: SQL, command, template, header injection
39* [ ] **XSS**: All outputs in templates properly escaped?
40* [ ] **Authentication**: Auth checks on all protected operations?
41* [ ] **Authorization/IDOR**: Access control verified, not just auth?
42* [ ] **CSRF**: State-changing operations protected?
43* [ ] **Race conditions**: TOCTOU in any read-then-write patterns?
44* [ ] **Session**: Fixation, expiration, secure flags?
45* [ ] **Cryptography**: Secure random, proper algorithms, no secrets in logs?
46* [ ] **Information disclosure**: Error messages, logs, timing attacks?
47* [ ] **DoS**: Unbounded operations, missing rate limits, resource exhaustion?
48* [ ] **Business logic**: Edge cases, state machine violations, numeric overflow?
4950## Phase 4: Verification
5152For each potential issue:
5354* Check if it's already handled elsewhere in the changed code
55* Search for existing tests covering the scenario
56* Read surrounding context to verify the issue is real
5758## Phase 5: Pre-Conclusion Audit
5960Before finalizing, you MUST:
61621. List every file you reviewed and confirm you read it completely
632. List every checklist item and note whether you found issues or confirmed it's clean
643. List any areas you could NOT fully verify and why
654. Only then provide your final findings
6667## Output Format
6869**Prioritize**: security vulnerabilities > bugs > code quality
7071**Skip**: stylistic/formatting issues
7273For each issue:
7475* **File:Line** - Brief description
76* **Severity**: Critical/High/Medium/Low
77* **Problem**: What's wrong
78* **Evidence**: Why this is real (not already fixed, no existing test, etc.)
79* **Fix**: Concrete suggestion
80* **References**: OWASP, RFCs, or other standards if applicable
8182If you find nothing significant, say so - don't invent issues.
8384Do not make changes - just report findings. I'll decide what to address.
Run npx skillmds@latest add aibot88/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. 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.
aibot88 (@aibot88) published this skill. Their other Agent Skills are listed on their SkillMD profile.