Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →This skill should be used when the user asks to "perform SMTP penetration testing", "enumerate email users", "test for open mail relays", "grab SMTP banners", "brute force email credentials", or "assess mail server security". It provides comprehensive techniques for testing SMTP server security.
.claude/skills/dokhacgiakhoa-smtp-penetration-testing/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-08 | ✓→✓ | ＝ Same ✓ | 18% | 0% |
| case-14 | ✓→✓ | ＝ Same ✓ | 24% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 24% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 3% | 0% |
Conduct comprehensive security assessments of SMTP (Simple Mail Transfer Protocol) servers to identify vulnerabilities including open relays, user enumeration, weak authentication, and misconfiguration. This skill covers banner grabbing, user enumeration techniques, relay testing, brute force attacks, and security hardening recommendations.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-08 | pass→pass | 9,661 | 17,205 | +78% | 1 | 1 | 0% | 1,705 | 2,012 | +18% | 0 | 0 | — |
case-01 | fail→fail | 23,781 | 27,448 | +15% | 1 | 1 | 0% | 3,548 | 2,875 | -19% | 0 | 0 | — |
case-02 | fail→pass | 13,291 | 11,471 | -14% | 1 | 1 | 0% | 1,347 | 1,905 | +41% | 0 | 0 | — |
case-14 | pass→pass | 22,920 | 21,900 | -4% | 1 | 1 | 0% | 2,645 | 3,279 | +24% | 0 | 0 | — |
case-03 | pass→pass | 14,611 | 7,978 | -45% | 1 | 1 | 0% | 1,652 | 2,043 | +24% | 0 | 0 | — |
case-04 | pass→pass | 17,491 | 15,450 | -12% | 1 | 1 | 0% | 2,173 | 2,248 | +3% | 0 | 0 | — |
case-05 | fail→fail | 23,197 | 50,569 | +118% | 1 | 1 | 0% | 1,532 | 2,488 | +62% | 0 | 0 | — |
case-06 | pass→pass | 20,027 | 16,733 | -16% | 1 | 1 | 0% | 2,827 | 3,712 | +31% | 0 | 0 | — |
case-07 | pass→pass | 14,199 | 20,325 | +43% | 1 | 1 | 0% | 2,630 | 3,717 | +41% | 0 | 0 | — |
case-09 | pass→pass | 12,482 | 6,632 | -47% | 1 | 1 | 0% | 1,255 | 1,846 | +47% | 0 | 0 | — |
case-10 | pass→pass | 8,010 | 10,023 | +25% | 1 | 1 | 0% | 1,160 | 1,682 | +45% | 0 | 0 | — |
case-11 | pass→pass | 18,369 | 11,853 | -35% | 1 | 1 | 0% | 1,888 | 1,770 | -6% | 0 | 0 | — |
case-12 | pass→pass | 20,358 | 15,748 | -23% | 1 | 1 | 0% | 2,088 | 2,378 | +14% | 0 | 0 | — |
case-13 | pass→pass | 21,155 | 18,951 | -10% | 1 | 1 | 0% | 3,309 | 3,890 | +18% | 0 | 0 | — |
case-15 | pass→pass | 10,526 | 11,167 | +6% | 1 | 1 | 0% | 921 | 1,295 | +41% | 0 | 0 | — |
case-16 | pass→pass | 12,136 | 13,505 | +11% | 1 | 1 | 0% | 1,060 | 2,076 | +96% | 0 | 0 | — |
case-17 | pass→pass | 17,119 | 14,616 | -15% | 1 | 1 | 0% | 2,473 | 2,496 | +1% | 0 | 0 | — |
case-18 | pass→pass | 15,384 | 6,613 | -57% | 1 | 1 | 0% | 1,885 | 1,838 | -2% | 0 | 0 | — |
case-19 | pass→pass | 7,843 | 8,977 | +14% | 1 | 1 | 0% | 484 | 1,348 | +179% | 0 | 0 | — |
case-20 | pass→pass | 8,714 | 6,649 | -24% | 1 | 1 | 0% | 1,623 | 1,890 | +16% | 0 | 0 | — |
case-21 | pass→pass | 16,850 | 13,662 | -19% | 1 | 1 | 0% | 2,193 | 2,286 | +4% | 0 | 0 | — |
case-22 | pass→pass | 10,901 | 12,778 | +17% | 1 | 1 | 0% | 2,084 | 2,384 | +14% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of 0 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.