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: 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.4risk: unknown5source: community6metadata:7 source: https://skillmd.com/skills/antigravity/find-bugs8---910# Find Bugs1112Review changes on this branch for bugs, security vulnerabilities, and code quality issues.1314## When to Use15- You need a review focused on bugs, security issues, or risky code changes.16- The task involves auditing the current branch diff rather than implementing new behavior.17- You want a structured review process with checklist-driven verification against changed files.1819## Phase 1: Complete Input Gathering20211. 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 line233. List all files modified in this branch before proceeding2425## Phase 2: Attack Surface Mapping2627For each changed file, identify and list:2829* All user inputs (request params, headers, body, URL components)30* All database queries31* All authentication/authorization checks32* All session/state operations33* All external calls34* All cryptographic operations3536## Phase 3: Security Checklist (check EVERY item for EVERY file)3738* [ ] **Injection**: SQL, command, template, header injection39* [ ] **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: Verification5152For each potential issue:5354* Check if it's already handled elsewhere in the changed code55* Search for existing tests covering the scenario56* Read surrounding context to verify the issue is real5758## Phase 5: Pre-Conclusion Audit5960Before finalizing, you MUST:61621. List every file you reviewed and confirm you read it completely632. List every checklist item and note whether you found issues or confirmed it's clean643. List any areas you could NOT fully verify and why654. Only then provide your final findings6667## Output Format6869**Prioritize**: security vulnerabilities > bugs > code quality7071**Skip**: stylistic/formatting issues7273For each issue:7475* **File:Line** - Brief description76* **Severity**: Critical/High/Medium/Low77* **Problem**: What's wrong78* **Evidence**: Why this is real (not already fixed, no existing test, etc.)79* **Fix**: Concrete suggestion80* **References**: OWASP, RFCs, or other standards if applicable8182If you find nothing significant, say so - don't invent issues.8384Do not make changes - just report findings. I'll decide what to address.8586## Limitations87- Use this skill only when the task clearly matches the scope described above.88- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.89- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
Run npx get-skill add antigravity/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.
Review local branch changes for bugs, security vulnerabilities, and code quality issues using a structured checklist-driven process. It is listed under Security, Coding & Dev Tools, Code Review, Secure Coding, Vulnerability Scanning on SkillMD.
SkillMD's automated safety review verdict for this skill is PASS. 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, Cursor, OpenAI Codex, Gemini, Antigravity. 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.
Antigravity Skills (@antigravity) published this skill. Their other Agent Skills are listed on their SkillMD profile.