Audit History
gws-sheets - 5 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v5 Latest | Aug 5, 2026, 11:24 AM | No confirmed findings | 0 | No capability change |
| v4 | Jul 5, 2026, 03:38 PM | No confirmed findings | 0 | No capability change |
| v3 | Jul 5, 2026, 03:38 PM | No confirmed findings | 0 | No capability change |
| v2 | Jun 30, 2026, 01:56 AM | No confirmed findings | 1 | External commandsNetwork accessFilesystem access |
| v1 | Mar 26, 2026, 08:26 AM | No confirmed findings | 0 | Baseline |
Aug 5, 2026, 11:24 AM
All 23 static alerts are false positives caused by Markdown formatting, fixed documentation links, and legitimate gws CLI examples. No prompt injection, malicious command construction, unauthorized network code, or exploitable path traversal is present in SKILL.md.
Risk Factors
⚙️ External commands (15)
🌐 Network access (3)
📁 Filesystem access (3)
Jul 5, 2026, 03:38 PM
All static findings are false positives caused by Markdown code spans, relative documentation links, Google documentation URLs, and safe CLI examples. No prompt injection, malicious intent, credential harvesting, or data exfiltration behavior was found in SKILL.md.
Risk Factors
⚙️ External commands (15)
🌐 Network access (3)
📁 Filesystem access (3)
Jul 5, 2026, 03:38 PM
All static findings are false positives caused by Markdown code spans, relative documentation links, Google documentation URLs, and safe CLI examples. No prompt injection, malicious intent, credential harvesting, or data exfiltration behavior was found in SKILL.md.
Risk Factors
⚙️ External commands (15)
🌐 Network access (3)
📁 Filesystem access (3)
Jun 30, 2026, 01:56 AM
Static analysis flagged many high-risk patterns, but review found these are Markdown code spans, documentation links, and expected Google Workspace CLI examples. The real risk is capability based: the skill guides an agent to run external gws commands that can read or change Google Sheets data after user authorization.
Capability review items (1)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Static false positives ignored (1)
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
⚙️ External commands (2)
🌐 Network access (1)
📁 Filesystem access (2)
Detected Patterns
Mar 26, 2026, 08:26 AM
All static analysis findings are false positives. The skill is a documentation file for the official Google Workspace CLI (gws) tool. Detected patterns (external_commands, filesystem, network, weak_crypto) are triggered by legitimate CLI documentation syntax and Google Sheets API method names in documentation text, not actual dangerous code. No security concerns identified.