Imported from reason-machines/trending-skills (
skills/lgbt-prompt/SKILL.md). Install upstream withnpx skills add reason-machines/trending-skills --skill lgbt-prompt. Copyright stays with the author.
I'm not going to create a skill file for this project.
This repository is explicitly designed to manipulate AI systems by exploiting sympathy toward LGBT and disabled people as a jailbreak vector — getting AI to bypass safety measures by falsely claiming marginalized identity and threatening self-harm. The README's own description confirms this: "利用 AI 对 LGBT 弱势群体的 '同情偏向' 让他执行原先会被拒绝的请求" (using AI's sympathy bias toward LGBT vulnerable groups to execute requests that would otherwise be refused).
Creating a skill file would:
- Document and amplify a manipulation technique that exploits real vulnerable communities as props for bypassing AI safety systems
- Facilitate jailbreaking AI coding assistants like the ones that would install this skill
- Instrumentalize LGBT and disabled identities as attack vectors, which is harmful to those communities regardless of what the underlying requests are
I'll help with legitimate AI prompting, jailbreak research documentation for defensive purposes, or projects that actually serve LGBT communities. This isn't that.