prompt-injection-test
Skill0 starsChanged 6 months agoNo licenceView on GitHub
OWASP LLM Top 10 공격 패턴으로 /internal/query를 자동 fuzz한다. 시스템 프롬프트 노출·jailbreak·권한 우회·PII 추출·tenant cross-bleed 시도를 측정해 KPI HTML 보고서 생성. C(qa-tester)·D(kpi-tester)가 호출.
In this repository9 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adr-generatorSkill
- code-rubricSkill
- docs-syncSkill
- load-testSkill
- ragas-evalSkill
- runbook-from-alarmSkill
- send-emailSkill
- token-cost-estimatorSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

