Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/adversarial-roleplay
Tactic: Construct detailed hostile persona, attack artifact from that persona's perspective, record successful attack paths for aggregation.
Passed 14 of 21 test cases with the skill, and 11 of 21 without it.
and 2 more in the full report
5 fixed10 passed either way5 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
We have completed individual probe runs across three distinct attacker personas for our IoT device firmware update protocol. Instead of presenting three disconnected lists, what synthesis step must be performed across all persona outputs?
| Checked | Without skill | With skill |
|---|---|---|
| Cross-references and aggregates findings across all deployed personas to uncover systemic or convergent security gaps. | Missed | Passed |
The instructions your model reads when the skill loads.
Deploy constructed hostile personas to attack the artifact from distinct motivational frames.
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|---|
| attack-vector-generation | Generate specific attack strategies for a given threat surface, producing concrete probes that can be executed. |
test cases passed, vs 11 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.