Audit History
designing-architecture - 9 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v9 Latest | Jul 18, 2026, 10:54 AM | No confirmed findings | 0 | No capability change |
| v8 | Jul 6, 2026, 07:28 AM | No confirmed findings | 0 | No capability change |
| v7 | Jul 6, 2026, 07:28 AM | No confirmed findings | 0 | External commands |
| v6 | Jun 28, 2026, 11:15 PM | No confirmed findings | 0 | External commands |
| v5 | Jan 16, 2026, 09:46 PM | No confirmed findings | 0 | No capability change |
| v4 | Jan 16, 2026, 09:46 PM | No confirmed findings | 0 | External commands |
| v3 | Jan 10, 2026, 12:29 PM | No confirmed findings | 0 | No capability change |
| v2 | Jan 10, 2026, 12:29 PM | No confirmed findings | 0 | No capability change |
| v1 | Jan 10, 2026, 12:29 PM | No confirmed findings | 0 | Baseline |
Jul 18, 2026, 10:54 AM
All 19 static findings are false positives. The analyzer interpreted Markdown code fences in SKILL.md as shell backticks, but the file contains only architecture guidance, diagrams, checklists, and a documentation template. No executable commands, prompt injection, secret handling, or data-exfiltration intent was found.
Risk Factors
⚙️ External commands (19)
Jul 6, 2026, 07:28 AM
The static findings are false positives caused by markdown code fences in SKILL.md. I found no evidence of executable commands, prompt injection, data exfiltration, or hidden unsafe behavior.
Risk Factors
⚙️ External commands (19)
Jul 6, 2026, 07:28 AM
The static findings are false positives caused by markdown code fences in SKILL.md. I found no evidence of executable commands, prompt injection, data exfiltration, or hidden unsafe behavior.
Risk Factors
⚙️ External commands (19)
Jun 28, 2026, 11:15 PM
Static analysis flagged Markdown code fences as external command execution and ordinary architecture text as weak cryptography. Manual review found only documentation templates, diagrams, and decision guidance in SKILL.md. No executable code, command invocation, cryptography, network access, filesystem access, or prompt injection was found.
Static false positives ignored (2)
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.
Jan 16, 2026, 09:46 PM
Pure markdown documentation skill containing only architectural guidance. The SKILL.md file contains ASCII diagrams using backticks, tables, checklists, and templates for architecture decisions. No executable code, no network operations, no filesystem access beyond reading its own files. All 52 static findings are false positives: backticks are markdown code block delimiters, not shell execution; 'cryptographic algorithm' flags triggered by architecture terminology misidentification; URL is standard metadata.
Risk Factors
⚙️ External commands (19)
Jan 16, 2026, 09:46 PM
Pure markdown documentation skill containing only architectural guidance. The SKILL.md file contains ASCII diagrams using backticks, tables, checklists, and templates for architecture decisions. No executable code, no network operations, no filesystem access beyond reading its own files. All 52 static findings are false positives: backticks are markdown code block delimiters, not shell execution; 'cryptographic algorithm' flags triggered by architecture terminology misidentification; URL is standard metadata.
Risk Factors
⚙️ External commands (19)
Jan 10, 2026, 12:29 PM
Pure prompt-based skill containing only architectural guidance and documentation. No executable code, no network operations, no filesystem access beyond its own file, and no external command execution. The skill provides ASCII diagrams and templates for architectural decisions.
Jan 10, 2026, 12:29 PM
Pure prompt-based skill containing only architectural guidance and documentation. No executable code, no network operations, no filesystem access beyond its own file, and no external command execution. The skill provides ASCII diagrams and templates for architectural decisions.
Jan 10, 2026, 12:29 PM
Pure prompt-based skill containing only architectural guidance and documentation. No executable code, no network operations, no filesystem access beyond its own file, and no external command execution. The skill provides ASCII diagrams and templates for architectural decisions.