Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →BurpSuite Integration
.claude/skills/shadd0wtaka-burpsuite/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -59% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 38% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -60% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -72% | 0% |
BurpSuite Integration
Category: scanning — Web Application Testing
BurpSuite Integration
pythonfrom tools.burpsuite_integration import BurpSuiteAPI async def main(): tool = BurpSuiteAPI() result = await tool.__init__("target.com") print(result)
pythonfrom tools.burpsuite_integration import BurpSuiteHeadless async def main(): tool = BurpSuiteHeadless() result = await tool.__init__("target.com") print(result)
bashburpsuite --help
deep-recon --tool burpsuite_integration --target example.comscanningzen-agents_agent_run agent_type=scanning tool=burpsuite_integrationPOST /tools/execute with {"tool_name": "burpsuite_integration", "target": "example.com"}| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | fail→pass | 10,705 | 2,471 | -77% | 1 | 1 | 0% | 1,725 | 705 | -59% | 0 | 0 | — |
case-01 | fail→pass | 8,040 | 8,291 | +3% | 1 | 1 | 0% | 1,199 | 1,650 | +38% | 0 | 0 | — |
case-02 | fail→fail | 7,260 | 8,208 | +13% | 1 | 1 | 0% | 649 | 957 | +47% | 0 | 0 | — |
case-03 | fail→fail | 6,298 | 10,253 | +63% | 1 | 1 | 0% | 522 | 1,245 | +139% | 0 | 0 | — |
case-05 | fail→pass | 9,111 | 3,244 | -64% | 1 | 1 | 0% | 1,516 | 866 | -43% | 0 | 0 | — |
case-06 | fail→pass | 6,671 | 1,978 | -70% | 1 | 1 | 0% | 1,182 | 471 | -60% | 0 | 0 | — |
case-07 | fail→pass | 12,609 | 2,345 | -81% | 1 | 1 | 0% | 2,054 | 585 | -72% | 0 | 0 | — |
case-08 | fail→pass | 9,785 | 2,076 | -79% | 1 | 1 | 0% | 1,636 | 550 | -66% | 0 | 0 | — |
case-09 | fail→pass | 10,686 | 2,070 | -81% | 1 | 1 | 0% | 2,003 | 566 | -72% | 0 | 0 | — |
case-10 | fail→pass | 12,346 | 1,652 | -87% | 1 | 1 | 0% | 1,863 | 496 | -73% | 0 | 0 | — |
case-11 | fail→pass | 10,298 | 3,692 | -64% | 1 | 1 | 0% | 2,055 | 876 | -57% | 0 | 0 | — |
case-12 | fail→pass | 4,974 | 5,715 | +15% | 1 | 1 | 0% | 837 | 1,361 | +63% | 0 | 0 | — |
case-13 | fail→pass | 8,261 | 2,224 | -73% | 1 | 1 | 0% | 1,203 | 593 | -51% | 0 | 0 | — |
case-14 | pass→pass | 6,837 | 1,729 | -75% | 1 | 1 | 0% | 1,038 | 532 | -49% | 0 | 0 | — |
case-15 | fail→pass | 8,644 | 2,257 | -74% | 1 | 1 | 0% | 1,504 | 620 | -59% | 0 | 0 | — |
case-16 | pass→pass | 11,467 | 4,956 | -57% | 1 | 1 | 0% | 2,068 | 1,149 | -44% | 0 | 0 | — |
case-17 | fail→pass | 11,423 | 3,648 | -68% | 1 | 1 | 0% | 1,672 | 837 | -50% | 0 | 0 | — |
case-18 | fail→pass | 4,596 | 1,143 | -75% | 1 | 1 | 0% | 704 | 413 | -41% | 0 | 0 | — |
case-19 | fail→pass | 9,233 | 11,218 | +21% | 1 | 1 | 0% | 1,701 | 473 | -72% | 0 | 0 | — |
case-20 | pass→pass | 15,715 | 11,653 | -26% | 1 | 1 | 0% | 3,186 | 2,446 | -23% | 0 | 0 | — |
case-21 | fail→fail | 18,189 | 15,277 | -16% | 1 | 1 | 0% | 1,372 | 1,860 | +36% | 0 | 0 | — |
case-22 | pass→fail | 11,751 | 11,058 | -6% | 1 | 1 | 0% | 2,108 | 2,367 | +12% | 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 +64 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.