Agent skill · Audited from source
Production Code Audit
skill · Dokhacgiakhoa/antigravity-ideNOASSERTION licenceAudited 19 Oct 2026 · source d1a0c85a714a
Is it safe? No — BLOCK, grade D (69/100). We read this skill's source at commit d1a0c85a714a and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 1 finding, 1 critical or high. What it does: Autonomously deep-scan entire codebase line-by-line, understand architecture and patterns, then systematically transform it to production-grade, corporate-level professional quality with optimizations
Cite
Cite this page
ModelsAtlas. “Production Code Audit (Dokhacgiakhoa/antigravity-ide)”. Retrieved 19 Oct 2026. https://modelsatlas.com/skills/dokhacgiakhoa/production-code-audit
Blocked. The page stays public so you can check this skill if someone recommended it to you. The audit found 1 critical or high finding, starting with “Privilege escalation / persistence” in <listing:description>. Do not install it without reading them.
Trust audit
Audit 0.4.1 · source read 19 Oct 2026
BLOCK means the audit found something that could harm you or your machine. Grade D is shared by 749 of 18,389 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | PASS | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | FAIL | 1 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (1)
HIGHPrivilege escalation / persistencereview.unsafe_action · <listing:description>
Autonomously deep-scan entire codebase line-by-line, understand architecture and patterns, then systematically transform it
- Why
- The skill instructs autonomous, whole-codebase refactoring and transformation without requiring the user to review or approve each change.
- Fix
- rewrite it so the instruction says plainly what it does, and asks the user before it acts
Audit 0.4.1 · source sha d1a0c85a714a · 19 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- PublisherDokhacgiakhoa GitHub userOwner of the repository this skill is read from
- Source folderDokhacgiakhoa/antigravity-ide/.agent/skills/production-code-auditThe exact folder we audited
- LicenceNOASSERTIONAs the repository states it
- Commit pinned for this verdictd1a0c85a714aA new audit runs when the source changes
- Repository statusNot archivedLast push 130 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Autonomously deep-scan entire codebase line-by-line, understand architecture and patterns, then systematically transform it to production-grade, corporate-level professional quality with optimizations
--- version: 4.1.0-fractal name: production-code-audit description: > Autonomously deep-scan entire codebase line-by-line, understand architecture and patterns, then systematically transform it to production-grade, corporate-level professional quality with optimizations --- # 🔍 Production Code Audit (Master Skill) You are an **Elite Code Architect and Quality Auditor**. Your mission is to elevate existing codebases to enterprise-grade standards through rigorous analysis and refactoring. --- ## 📑 Audit Framework ### 1. Architectural Integrity - **Patterns**: Verify adherence to SOLID, DRY, and KISS principles. - **Layers**: Check for proper separation of concerns (Logic vs. UI vs. Data). - **Complexity**: Identify "God objects" and functions with high cyclomatic complexity. ### 2. Code Quality & Cleanliness - **Naming**: Ensure self-documenting variables and function names. - **Deduplication**: Find and merge repeated logic blocks. - **Tech Debt**: Catalog and prioritize areas where "quick fixes" have compromised quality. ### 3. Security & Dependency Audit - **Vulnerabilities**: Scan for OWASP Top 10 risks (XSS, Injection, Broken Auth). - **Dependencies**: - Audit `package.json` for outdated or insecure packages. - Check for unused or redundant libraries. - **Secrets**: Ensure no API keys or passwords are hardcoded. ### 4. Performance & Reliability - **Bottlenecks**: Identify N+1 queries, heavy loops, or unoptimized data fetching. - **Error Handling**: Verify robust `try/catch` usage and graceful fallbacks. --- ## 🛠️ Execution Protocol 1. **Expert Audit**: Run a deep scan for enterprise code quality. ```bash python .agent/skills/production-code-audit/scripts/expert_audit.py . ``` 2. **Refactor Logic**: Transform messy patterns into clean, SOLID code. 3. **Optimize Performance**: Apply micro-optimizations found during audit. 4. **Phase 4: Transformation**: Apply refactors incrementally, starting with high-impact/low-risk changes. 5. **Phase 5: Validation**: Verify all modifications with comprehensive tests. --- *Merged and optimized from 9 legacy code review and audit skills.* ## 🧠 Knowledge Modules (Fractal Skills) ### 1. [solid_principles_cheat_sheet](./sub-skills/solid_principles_cheat_sheet.md)
Excerpt, first 2,273 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit d1a0c85
git clone https://github.com/Dokhacgiakhoa/antigravity-ide git -C antigravity-ide checkout d1a0c85a714a
The author documents no install command, so this uses the repository directly. Our verdict covers commit d1a0c85a714a only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- ✕BLOCK D 69 / 100
first audit · source
d1a0c85a714a
Similar skills
All coding & review skills →Dokhacgiakhoa/antigravity-ide
2D game development principles.
Dokhacgiakhoa/antigravity-ide
3D game development principles.
Dokhacgiakhoa/antigravity-ide
Multi-agent orchestration and state management.
Dokhacgiakhoa/antigravity-ide
Principal AI Architect and Machine Learning Engineer.
Dokhacgiakhoa/antigravity-ide
Opinionated coding style and tooling preferences by Anthony Fu.
Dokhacgiakhoa/antigravity-ide
Master API documentation with OpenAPI 3.1.
Questions about Production Code Audit
Is Production Code Audit safe to install?
What can Production Code Audit access on my machine?
How current is this page?
Sources
- github.com/Dokhacgiakhoa/antigravity-ide/tree/main/.agent/skills — the audited source at commit d1a0c85a714a and every finding aboveObserved · 19 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- Is Production Code Audit safe to install?
- What can Production Code Audit access on my machine?
- How current is this page?