Audit History
arch-tech-evaluation - 4 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v4 Latest | Jul 24, 2026, 02:10 AM | No confirmed findings | 0 | No capability change |
| v3 | Jul 15, 2026, 02:54 PM | No confirmed findings | 0 | No capability change |
| v2 | Jul 15, 2026, 02:54 PM | No confirmed findings | 0 | No capability change |
| v1 | Jul 15, 2026, 02:54 PM | No confirmed findings | 0 | Baseline |
Jul 24, 2026, 02:10 AM
All four static findings are false positives. The command alerts identify Markdown fences, while the entropy alerts identify readable Chinese Markdown rather than encoded payloads. No prompt injection, data exfiltration, or executable behavior was found.
Risk Factors
⚙️ External commands (2)
Jul 15, 2026, 02:54 PM
All four static findings are false positives. The backticks are Markdown fences, while both files contain readable Chinese Markdown rather than obfuscated content. No semantic security issue was found.
Risk Factors
⚙️ External commands (2)
Jul 15, 2026, 02:54 PM
All four static findings are false positives. The backticks are Markdown fences, while both files contain readable Chinese Markdown rather than obfuscated content. No semantic security issue was found.
Risk Factors
⚙️ External commands (2)
Jul 15, 2026, 02:54 PM
All four static findings are false positives. The backticks are Markdown fences, while both files contain readable Chinese Markdown rather than obfuscated content. No semantic security issue was found.