Audit History
search-term-miner - 6 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v6 Latest | Jul 27, 2026, 11:42 AM | No confirmed findings | 0 | No capability change |
| v5 | Jul 13, 2026, 02:50 PM | No confirmed findings | 0 | No capability change |
| v4 | Jul 13, 2026, 02:50 PM | No confirmed findings | 0 | No capability change |
| v3 | Jul 12, 2026, 01:55 PM | No confirmed findings | 0 | No capability change |
| v2 | Jul 6, 2026, 07:01 PM | No confirmed findings | 0 | No capability change |
| v1 | Jul 4, 2026, 04:22 PM | No confirmed findings | 0 | Baseline |
Jul 27, 2026, 11:42 AM
All 35 static detections are false positives caused by Markdown backticks, relative documentation links, and repository metadata. The skill describes analysis of a user-provided paid-search export and requires confirmation before saving a workspace summary. No executable command, network request, path traversal operation, reconnaissance behavior, or prompt injection attempt was found.
Risk Factors
βοΈ External commands (14)
π Network access (2)
Jul 13, 2026, 02:50 PM
All 35 static findings are false positives caused by Markdown backticks, repository URLs, relative documentation links, or ordinary marketing terminology. The skill contains no executable code or network request and limits file writing to a documented local report after user confirmation. No malicious intent, prompt injection, data exfiltration, or system reconnaissance was found.
Risk Factors
βοΈ External commands (14)
π Network access (2)
Jul 13, 2026, 02:50 PM
All 35 static findings are false positives caused by Markdown backticks, repository URLs, relative documentation links, or ordinary marketing terminology. The skill contains no executable code or network request and limits file writing to a documented local report after user confirmation. No malicious intent, prompt injection, data exfiltration, or system reconnaissance was found.
Risk Factors
βοΈ External commands (14)
π Network access (2)
Jul 12, 2026, 01:55 PM
All 35 static alerts are false positives caused by Markdown formatting, repository URLs, and fixed relative documentation links. No executable command, automatic network request, prompt injection, reconnaissance, or arbitrary path access is present.
Risk Factors
βοΈ External commands (14)
π Network access (2)
Jul 6, 2026, 07:01 PM
The static findings are false positives caused by Markdown formatting, inline code tokens, hardcoded homepage metadata, and relative documentation links. I found no executable shell commands, active network request, arbitrary path traversal, or prompt injection attempt in SKILL.md. The skill processes user-provided ad exports, so normal untrusted-input handling remains important.
Risk Factors
βοΈ External commands (12)
π Network access (2)
Jul 4, 2026, 04:22 PM
All static findings were adjudicated as false positives after reviewing SKILL.md. The alerts are Markdown fences, inline code formatting, fixed repository links, homepage metadata, and a constrained memory save path. No prompt injection, data exfiltration intent, command execution, or unsafe filesystem behavior was found.