Audit History
refactor-code - 8 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v8 Latest | 2026年7月5日 上午07:42 | No confirmed findings | 0 | No capability change |
| v7 | 2026年7月5日 上午07:42 | No confirmed findings | 0 | Network access Filesystem access |
| v6 | 2026年6月29日 上午02:40 | 2 confirmed | 0 | Filesystem access Network access |
| v5 | 2026年1月16日 下午11:12 | No confirmed findings | 0 | No capability change |
| v4 | 2026年1月16日 下午11:12 | No confirmed findings | 0 | Network accessExternal commands |
| v3 | 2026年1月10日 下午12:56 | No confirmed findings | 0 | No capability change |
| v2 | 2026年1月10日 下午12:56 | No confirmed findings | 0 | No capability change |
| v1 | 2026年1月10日 下午12:56 | No confirmed findings | 0 | Baseline |
2026年7月5日 上午07:42
Manual review found no malicious intent, prompt injection, data exfiltration, or hidden executable payloads in SKILL.md. The static findings are false positives from Markdown fences, inline code formatting, sample Java and TypeScript code, local development commands, and a localhost URL.
Risk Factors
⚙️ External commands (33)
🌐 Network access (1)
2026年7月5日 上午07:42
Manual review found no malicious intent, prompt injection, data exfiltration, or hidden executable payloads in SKILL.md. The static findings are false positives from Markdown fences, inline code formatting, sample Java and TypeScript code, local development commands, and a localhost URL.
Risk Factors
⚙️ External commands (33)
🌐 Network access (1)
2026年6月29日 上午02:40
Static analysis reported many high-risk patterns, but review found no malicious intent or prompt injection. Most detections are Markdown code fences, documentation examples, Japanese text, or localhost documentation; the remaining real risk is that the skill instructs agents to edit files and run repository commands during refactoring.
Confirmed security concerns (2)
Static false positives ignored (4)
These static matches were dismissed by semantic review or matched schema-only tokens, so they are shown for transparency but do not drive the quality score.
Risk Factors
📁 Filesystem access (2)
⚙️ External commands (4)
Detected Patterns
2026年1月16日 下午11:12
This skill is pure markdown documentation providing refactoring guidance and workflow instructions. All 54 static findings are false positives: substring detection triggered on 'DES' in 'DRY', 'RC4' in 'MCP', hashes containing letter patterns; backtick detection on markdown code blocks; and high entropy from Japanese text with code samples. No executable code, no network calls, no malicious patterns.
Risk Factors
🌐 Network access (1)
⚙️ External commands (34)
2026年1月16日 下午11:12
This skill is pure markdown documentation providing refactoring guidance and workflow instructions. All 54 static findings are false positives: substring detection triggered on 'DES' in 'DRY', 'RC4' in 'MCP', hashes containing letter patterns; backtick detection on markdown code blocks; and high entropy from Japanese text with code samples. No executable code, no network calls, no malicious patterns.
Risk Factors
🌐 Network access (1)
⚙️ External commands (34)
2026年1月10日 下午12:56
This skill is a pure markdown prompt file with no executable code. It provides refactoring guidance and workflow instructions for AI agents. No network calls, no file system access beyond standard framework tools, no external commands, no environment variable access patterns.
2026年1月10日 下午12:56
This skill is a pure markdown prompt file with no executable code. It provides refactoring guidance and workflow instructions for AI agents. No network calls, no file system access beyond standard framework tools, no external commands, no environment variable access patterns.
2026年1月10日 下午12:56
This skill is a pure markdown prompt file with no executable code. It provides refactoring guidance and workflow instructions for AI agents. No network calls, no file system access beyond standard framework tools, no external commands, no environment variable access patterns.