Installs into .claude/skills of the current project.
Are you the author of Auto Security Learning Detecting Prompt?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/openamer-auto-security-learning-detecting-prompt)
---
name: auto-security-learning-detecting-prompt
description: "PVDetector, a training-free framework that detects PI attacks during LLM inference by measuring hidd GAP: no mappable capability in latest signal (our"
auto_generated: true
created: 2026-09-18
source_insight: "Security learning (Detecting prompt injection attacks in LLMs using adversarial examples): What shou"
status: draft
fitness_score: 0
trials: 0
wins: 0
---
# Auto Security Learning Detecting Prompt
## Trigger
Use when the agent encounters: PVDetector, a training-free framework that detects PI attacks during LLM inference by measuring hidd
## Verification
- [ ] The skill produces the expected output for its domain
- [ ] No errors in execution
- [ ] Insight quality: actionable and specific
## Notes
Auto-generated from internet insight (Knowledge-to-Action pipeline).
Darwin will trial this skill; it gets promoted only if it wins arena fights.
