Audit History
search-engineer - 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, 12:00 AM | No confirmed findings | 1 | No capability change |
| v3 | Jul 15, 2026, 03:38 PM | No confirmed findings | 1 | No capability change |
| v2 | Jul 15, 2026, 03:38 PM | No confirmed findings | 1 | No capability change |
| v1 | Jul 15, 2026, 03:38 PM | No confirmed findings | 1 | Baseline |
Jul 24, 2026, 12:00 AM
The 25 external-command findings are false positives caused by Markdown code fences; the document does not use Ruby or shell backtick execution. The pinned third-party plugin installation is a genuine low-severity network and supply-chain risk because no checksum or signature verification is provided.
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.
Risk Factors
⚙️ External commands (25)
🌐 Network access (1)
Jul 15, 2026, 03:38 PM
All 25 external-command findings are false positives caused by Markdown code fences, not Ruby or shell backtick execution. The remote plugin installation URL is a legitimate example, but installing an unchecked archive creates a low-severity supply-chain risk.
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.
Risk Factors
⚙️ External commands (25)
🌐 Network access (1)
Jul 15, 2026, 03:38 PM
All 25 external-command findings are false positives caused by Markdown code fences, not Ruby or shell backtick execution. The remote plugin installation URL is a legitimate example, but installing an unchecked archive creates a low-severity supply-chain risk.
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.
Risk Factors
⚙️ External commands (25)
🌐 Network access (1)
Jul 15, 2026, 03:38 PM
All 25 external-command findings are false positives caused by Markdown code fences, not Ruby or shell backtick execution. The remote plugin installation URL is a legitimate example, but installing an unchecked archive creates a low-severity supply-chain risk.
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.