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.
Limitations
Use this skill only when the task clearly matches the scope described above.
Do not treat the output as a substitute for enprojectnment-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: 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 Bugs78Review changes on this branch for bugs, security vulnerabilities, and code quality issues.910## When to Use11- You need a review focused on bugs, security issues, or risky code changes.12- The task involves auditing the current branch diff rather than implementing new behavior.13- You want a structured review process with checklist-driven verification against changed files.1415## Phase 1: Complete Input Gathering16171. Get the FULL diff: `git diff $(gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name')...HEAD`182. If output is truncated, read each changed file individually until you have seen every changed line193. List all files modified in this branch before proceeding2021## Phase 2: Attack Surface Mapping2223For each changed file, identify and list:2425* All user inputs (request params, headers, body, URL components)26* All database queries27* All authentication/authorization checks28* All session/state operations29* All external calls30* All cryptographic operations3132## Phase 3: Security Checklist (check EVERY item for EVERY file)3334* [ ] **Injection**: SQL, command, template, header injection35* [ ] **XSS**: All outputs in templates properly escaped?36* [ ] **Authentication**: Auth checks on all protected operations?37* [ ] **Authorization/IDOR**: Access control verified, not just auth?38* [ ] **CSRF**: State-changing operations protected?39* [ ] **Race conditions**: TOCTOU in any read-then-write patterns?40* [ ] **Session**: Fixation, expiration, secure flags?41* [ ] **Cryptography**: Secure random, proper algorithms, no secrets in logs?42* [ ] **Information disclosure**: Error messages, logs, timing attacks?43* [ ] **DoS**: Unbounded operations, missing rate limits, resource exhaustion?44* [ ] **Business logic**: Edge cases, state machine violations, numeric overflow?4546## Phase 4: Verification4748For each potential issue:4950* Check if it's already handled elsewhere in the changed code51* Search for existing tests covering the scenario52* Read surrounding context to verify the issue is real5354## Phase 5: Pre-Conclusion Audit5556Before finalizing, you MUST:57581. List every file you reviewed and confirm you read it completely592. List every checklist item and note whether you found issues or confirmed it's clean603. List any areas you could NOT fully verify and why614. Only then provide your final findings6263## Output Format6465**Prioritize**: security vulnerabilities > bugs > code quality6667**Skip**: stylistic/formatting issues6869For each issue:7071* **File:Line** - Brief description72* **Severity**: Critical/High/Medium/Low73* **Problem**: What's wrong74* **Evidence**: Why this is real (not already fixed, no existing test, etc.)75* **Fix**: Concrete suggestion76* **References**: OWASP, RFCs, or other standards if applicable7778If you find nothing significant, say so - don't invent issues.7980Do not make changes - just report findings. I'll decide what to address.8182## Limitations83- Use this skill only when the task clearly matches the scope described above.84- Do not treat the output as a substitute for enprojectnment-specific validation, testing, or expert review.85- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
Run npx skillmds add phoroth/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, and the skill stays under its author's original license.
phoroth (@phoroth) published this skill. Their other Agent Skills are listed on their SkillMD profile.