Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Conduct red team operations using the Covenant C2 framework for authorized adversary simulation, including listener setup, grunt deployment, task execution, and lateral movement tracking.
.claude/skills/performing-red-team-with-covenant/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-17 | ✗→✓ | ▲ Improved | — | — |
| case-12 | ✗→✓ | ▲ Improved | — | — |
| case-02 | ✓→✓ | = Same ✓ | — | — |
| case-01 | ✓→✓ | = Same ✓ | — | — |
| case-09 | ✓→✓ | = Same ✓ | — | — |
Covenant is a collaborative .NET C2 framework for red teamers that provides a Swagger-documented REST API for managing listeners, launchers, grunts (agents), and tasks. This skill covers automating Covenant operations through its API for authorized red team engagements: creating HTTP/HTTPS listeners, generating binary and PowerShell launchers, deploying grunts, executing tasks on compromised hosts, and tracking lateral movement.
requests libraryObtain a JWT token by posting credentials to /api/users/login endpoint.
Configure an HTTP or HTTPS listener with callback URLs and bind address.
Create a binary, PowerShell, or MSBuild launcher tied to the listener for grunt deployment.
Monitor grunt callbacks, execute tasks, and collect output from compromised hosts.
Generate an operations report documenting all actions, timestamps, and findings.
JSON report with listener configuration, active grunts, executed tasks, and task output for engagement documentation.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
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, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of 0 percentage points is the difference between those two pass rates over the 21 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.