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.
Limitations
Use this skill only when the task clearly matches the scope described above.
Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
1---2name: find-bugs3description: ALWAYS use this when the request matches Find Bugs: Find bugs, security vulnerabilities, and code quality issues in local branch changes.4---56# Find Bugs78## Selective Reading Rule910Start with:1112- `references/senior-master-standard.md`13- `references/usage-routing.md`14- `references/quality-checklist.md`1516Then load only the inherited docs, scripts, assets, or examples that match the user's actual task.1718Review changes on this branch for bugs, security vulnerabilities, and code quality issues.1920## When to Use21- You need a review focused on bugs, security issues, or risky code changes.22- The task involves auditing the current branch diff rather than implementing new behavior.23- You want a structured review process with checklist-driven verification against changed files.2425## Phase 1: Complete Input Gathering26271. Get the FULL diff: `git diff $(gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name')...HEAD`282. If output is truncated, read each changed file individually until you have seen every changed line293. List all files modified in this branch before proceeding3031## Phase 2: Attack Surface Mapping3233For each changed file, identify and list:3435* All user inputs (request params, headers, body, URL components)36* All database queries37* All authentication/authorization checks38* All session/state operations39* All external calls40* All cryptographic operations4142## Phase 3: Security Checklist (check EVERY item for EVERY file)4344* [ ] **Injection**: SQL, command, template, header injection45* [ ] **XSS**: All outputs in templates properly escaped?46* [ ] **Authentication**: Auth checks on all protected operations?47* [ ] **Authorization/IDOR**: Access control verified, not just auth?48* [ ] **CSRF**: State-changing operations protected?49* [ ] **Race conditions**: TOCTOU in any read-then-write patterns?50* [ ] **Session**: Fixation, expiration, secure flags?51* [ ] **Cryptography**: Secure random, proper algorithms, no secrets in logs?52* [ ] **Information disclosure**: Error messages, logs, timing attacks?53* [ ] **DoS**: Unbounded operations, missing rate limits, resource exhaustion?54* [ ] **Business logic**: Edge cases, state machine violations, numeric overflow?5556## Phase 4: Verification5758For each potential issue:5960* Check if it's already handled elsewhere in the changed code61* Search for existing tests covering the scenario62* Read surrounding context to verify the issue is real6364## Phase 5: Pre-Conclusion Audit6566Before finalizing, you MUST:67681. List every file you reviewed and confirm you read it completely692. List every checklist item and note whether you found issues or confirmed it's clean703. List any areas you could NOT fully verify and why714. Only then provide your final findings7273## Output Format7475**Prioritize**: security vulnerabilities > bugs > code quality7677**Skip**: stylistic/formatting issues7879For each issue:8081* **File:Line** - Brief description82* **Severity**: Critical/High/Medium/Low83* **Problem**: What's wrong84* **Evidence**: Why this is real (not already fixed, no existing test, etc.)85* **Fix**: Concrete suggestion86* **References**: OWASP, RFCs, or other standards if applicable8788If you find nothing significant, say so - don't invent issues.8990Do not make changes - just report findings. I'll decide what to address.9192## Limitations93- Use this skill only when the task clearly matches the scope described above.94- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.95- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
Run npx skillmds@latest add anhvu1107/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.
ALWAYS use this when the request matches Find Bugs: Find bugs, security vulnerabilities, and code quality issues in local branch changes. It is listed under AI & ML 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.
anhvu1107 (@anhvu1107) published this skill. Their other Agent Skills are listed on their SkillMD profile.