@andersmyrmel/vard

@andersmyrmel/vard is a TypeScript library for prompt injection detection in LLM applications. It uses a Zod-inspired chainable API: you define security requirements and validate user input, receiving strongly typed, sanitized data for use in LLM prompts. Detection is pattern-based and covers categories such as system prompt leaks, encoding attacks, and obfuscation. It offers presets (strict, moderate, lenient) with configurable thresholds, and threat actions including block, sanitize, warn, and allow.

Appearances
5
Categories
1
First seen
21 September 2026
Latest
11 October 2026
Saved risers · this browser →← All current risersGet this page's badge ↗Open source ↗

Recorded measurements

Published observations only. Missing dates are not zero, and points do not establish what happened between observations. Each source and unit is shown separately.

npm / PyPI packages · weekly downloads

npm / PyPI packages · 9 dated measurements

Rolling seven-day download totals recorded on these observation dates; do not add the points or treat their difference as new downloads.

Latest value shown: 27,008 weekly downloads ·

Higher values appear higher on the chart. The scale covers the recorded values.

npm / PyPI packages: weekly downloads recorded measurements9 dated points, 31 Aug 2026 to 11 Oct 2026. Values range from 12,950 to 41,146 weekly downloads. Higher values appear higher. Open the exact values and published evidence below for the data table. Dots are not connected; missing dates are not zero.31 Aug 2026: 20,220 weekly downloads13 Sept 2026: 12,950 weekly downloads21 Sept 2026: 19,151 weekly downloads22 Sept 2026: 19,397 weekly downloads1 Oct 2026: 33,301 weekly downloads2 Oct 2026: 36,287 weekly downloads3 Oct 2026: 41,146 weekly downloads10 Oct 2026: 24,196 weekly downloads11 Oct 2026: 27,008 weekly downloads
View 9 exact dated values and published evidence
Exact values and their published evidence
Measured onValue (weekly downloads)Published in
20,220
12,950
19,151
19,397
33,301
36,287
41,146
24,196
27,008

“Measured on” uses the original observation date. “Published in” links to the edition that reported it; the dates may differ.

01/

Appearance history

5 appearances
This page records every appearance of the same entity in the reviewed RiseFinder exports. Rankings keep the original category, period and measurement direction.

If you investigated this riser, tell us what helped—or what was missing.

Share feedback →
02/

Get email updates

Join the list

Get early signals on the websites, apps, repositories and startups gaining momentum. Join the list for Risefinder email briefings.

By subscribing, you ask us to store your email and send Risefinder updates. You can unsubscribe at any time. Privacy.

Want a sample first? Read past daily emails.