Audit History
plot-consistency-checker - 9 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v9 Latest | Jul 23, 2026, 06:33 AM | No confirmed findings | 0 | No capability change |
| v8 | Jul 7, 2026, 06:44 PM | No confirmed findings | 0 | No capability change |
| v7 | Jul 6, 2026, 03:00 AM | No confirmed findings | 0 | No capability change |
| v6 | Jun 28, 2026, 08:09 AM | No confirmed findings | 0 | No capability change |
| v5 | Jan 16, 2026, 03:49 PM | No confirmed findings | 0 | No capability change |
| v4 | Jan 16, 2026, 03:49 PM | No confirmed findings | 0 | No capability change |
| v3 | Jan 10, 2026, 10:19 AM | No confirmed findings | 0 | No capability change |
| v2 | Jan 10, 2026, 10:19 AM | No confirmed findings | 0 | No capability change |
| v1 | Jan 10, 2026, 10:19 AM | No confirmed findings | 0 | Baseline |
Jul 23, 2026, 06:33 AM
The prompt-only SKILL.md contains narrative review instructions without executable code, network access, secret handling, or privilege requests. No static or semantic security findings were identified, including prompt injection language.
Jul 7, 2026, 06:44 PM
No static findings were reported, so no finding verdicts are required. The reviewed SKILL.md contains prompt-only writing guidance and no prompt injection text, executable code, network use, or filesystem access.
Jul 6, 2026, 03:00 AM
Static analysis found no suspicious patterns in the prompt-only skill. Manual review of SKILL.md found no prompt injection, data exfiltration intent, or executable behavior.
Jun 28, 2026, 08:09 AM
Static analysis flagged weak cryptography at SKILL.md line 3, but the line is only descriptive frontmatter. I found no evidence of cryptographic code, scripts, network access, command execution, file operations, or prompt injection in the reviewed skill file.
Jan 16, 2026, 03:49 PM
This is a pure prompt-based skill containing only a SKILL.md instruction file with no executable code. All 11 static findings are false positives caused by the scanner misidentifying JSON field names and descriptive text (like 'magic systems' and 'source code') as cryptographic patterns. The source_url is metadata, not a network call. No network, filesystem, or command execution capabilities exist. The skill behavior matches the stated purpose exactly.
Jan 16, 2026, 03:49 PM
This is a pure prompt-based skill containing only a SKILL.md instruction file with no executable code. All 11 static findings are false positives caused by the scanner misidentifying JSON field names and descriptive text (like 'magic systems' and 'source code') as cryptographic patterns. The source_url is metadata, not a network call. No network, filesystem, or command execution capabilities exist. The skill behavior matches the stated purpose exactly.
Jan 10, 2026, 10:19 AM
This is a pure prompt-based skill containing only a SKILL.md instruction file. No executable code, network access, filesystem access, or external command execution capabilities. The behavior matches the stated purpose exactly.
Jan 10, 2026, 10:19 AM
This is a pure prompt-based skill containing only a SKILL.md instruction file. No executable code, network access, filesystem access, or external command execution capabilities. The behavior matches the stated purpose exactly.
Jan 10, 2026, 10:19 AM
This is a pure prompt-based skill containing only a SKILL.md instruction file. No executable code, network access, filesystem access, or external command execution capabilities. The behavior matches the stated purpose exactly.