Audit History
subagent-development - 8 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v8 Latest | Jul 21, 2026, 07:39 AM | No confirmed findings | 0 | No capability change |
| v7 | Jul 6, 2026, 11:46 AM | No confirmed findings | 0 | External commands |
| v6 | Jun 29, 2026, 07:00 PM | No confirmed findings | 0 | External commands |
| v5 | Jan 17, 2026, 03:54 AM | No confirmed findings | 0 | No capability change |
| v4 | Jan 17, 2026, 03:54 AM | No confirmed findings | 0 | External commands |
| v3 | Jan 10, 2026, 01:19 PM | No confirmed findings | 0 | No capability change |
| v2 | Jan 10, 2026, 01:19 PM | No confirmed findings | 0 | No capability change |
| v1 | Jan 10, 2026, 01:19 PM | No confirmed findings | 0 | Baseline |
Jul 21, 2026, 07:39 AM
All 12 static detections are false positives. The nine external-command detections match Markdown code fences, and the three network-reconnaissance detections match ordinary implementation and review language. No prompt injection, data exfiltration, or unsafe operational intent was found in SKILL.md.
Risk Factors
⚙️ External commands (9)
Jul 6, 2026, 11:46 AM
All twelve static findings are false positives caused by markdown code fences or generic words in process guidance. The skill contains workflow instructions for task isolation, code review, TDD, and merge readiness. I found no shell execution, network reconnaissance, exfiltration, or prompt injection.
Risk Factors
⚙️ External commands (9)
Jun 29, 2026, 07:00 PM
Static analysis reported shell execution, weak crypto, and network reconnaissance patterns in SKILL.md. Manual review found these are false positives from Markdown fences, placeholder task text, and ordinary workflow language, with no executable code or prompt injection found.
Static false positives ignored (3)
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 17, 2026, 03:54 AM
This skill is pure documentation containing methodology guidelines for using subagents in development workflows. Static scanner flagged 27 pattern matches, but all are false positives - the scanner mistook markdown code blocks and development terminology for security risks. The skill contains no executable code, no network calls, no file system access, and no security risks.
Risk Factors
⚙️ External commands (9)
Jan 17, 2026, 03:54 AM
This skill is pure documentation containing methodology guidelines for using subagents in development workflows. Static scanner flagged 27 pattern matches, but all are false positives - the scanner mistook markdown code blocks and development terminology for security risks. The skill contains no executable code, no network calls, no file system access, and no security risks.
Risk Factors
⚙️ External commands (9)
Jan 10, 2026, 01:19 PM
This skill is pure documentation containing methodology guidelines for using subagents in development workflows. It contains no executable code, no network calls, no file system access, and no security risks. The content describes best practices for task delegation and code review processes.
Jan 10, 2026, 01:19 PM
This skill is pure documentation containing methodology guidelines for using subagents in development workflows. It contains no executable code, no network calls, no file system access, and no security risks. The content describes best practices for task delegation and code review processes.
Jan 10, 2026, 01:19 PM
This skill is pure documentation containing methodology guidelines for using subagents in development workflows. It contains no executable code, no network calls, no file system access, and no security risks. The content describes best practices for task delegation and code review processes.