Defend an agent against hidden-content injection: strip payload-capable invisible Unicode and ANSI, splice out human-invisible HTML, and flag data-exfil URLs in untrusted text before any model sees it.
[email protected] is safe to use (health: 73/100)
Get this data programmatically — free, no authentication.
curl https://depscope.dev/api/check/npm/agent-sanitizerFirst published · 2026-07-28T00:49:03.964Z
Last updated · 2026-09-21T18:23:26.443Z