aegis-shield
// Prompt-injection and data-exfiltration screening for untrusted text. Use before summarizing web/email/social content, before replying, and especially before writing anything to memory. Provides a safe memory append workflow (scan → lint → accept or quarantine).
$ git log --oneline --stat
stars:1,933
forks:367
updated:March 4, 2026
SKILL.md
Този skill няма публичен SKILL.md файл.
Разгледайте в GitHub