Official descriptionPrompt-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).
Source
from SkillHub · type: agent skill
Harvest history
first seen 2026-10-09 · last seen 2026-10-16 · seen 12× · listed by 1 sources
Score
score 103 · 1 sources · skill
FAQ (answers come from our records)
How do I install it?
We did not find an install command for this repository (our install coverage is only about 4%). Check its README or releases page.
Who is it for?
We filed it under these tags: it-ops-security. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
first catalogued 2026-10-09;last seen 2026-10-16。There is no official certification or quality rating here — we record sources and dates only.