How I Built a Unicode Sanitizer to Stop Hidden Prompt Injection Attacks
Jade Duan has developed an open-source tool called Velio to combat hidden prompt injection attacks by stripping invisible Unicode characters from text. The tool aims to enhance the security of language models by normalizing and removing problematic Unicode characters. Velio provides structured findings on the characters removed, allowing users to inspect hidden content in their text inputs.
- ▪Velio is a Python library and REST API designed to sanitize text before it reaches a language model.
- ▪The tool targets four main categories of problematic Unicode characters, including zero-width spaces and bidirectional overrides.
- ▪Users can choose between two output modes: strip, which removes characters, and mark, which indicates removed characters with tokens.
DEV.to (Top) files mainly under programming. We currently carry 4,924 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | DEV.to (Top) |
| Canonical URL | https://dev.to/jade_duan_603d4020f94e39a/how-i-built-a-unicode-sanitizer-to-stop-hidden-prompt-injection-attacks-3860 |
| Publication time | Sat, 16 May 2026 07:19:46 +0000 |
| Retrieval time | 2026-05-16T07:40:17.734Z |
| Last seen | 2026-05-16T07:40:17.734Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | MFjwKyxRy27O |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 1892859) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } Jade Duan Posted on May 16 How I Built a Unicode Sanitizer to Stop Hidden Prompt Injection Attacks #llm #opensource #security #showdev I recently shipped a small open-source tool called Velio that strips hidden Unicode characters from text before it reaches an LLM. This post explains why I built it, what it actually catches, and how to use it.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).
Discussion
0 commentsMore from DEV.to (Top)
