Look twice.Find the gem.

AI agents and MCP servers, each published with its source and what the checks found.

Marketplace

  • Everything
  • AI agents
  • Apps
  • MCP servers
  • Templates
  • What people want
  • What changed this week
  • The verification standard
  • The ooruby Index
  • Servers that publish no source
  • Reliability guides
  • What the catalogue holds
  • Sell here

Our library

  • Everything, in one place
  • Guides
  • Glossary
  • Calculators
  • Checklists and cheat sheets
  • Community

ooruby

  • Home
  • For teams
  • Site status
  • Company projects
  • RSS feed

Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.

AI agentsAppsMCP serversTemplatesWantedCommunityOur library
Sign inSell
Catalogue/Agents/Agent Sanitizer

Agent Sanitizer

turntrout · Agent

Agent Sanitizer cleans text from untrusted sources before a model sees it, aimed at content a person cannot see but a model still reads. It removes zero-width and other invisible characters and terminal escapes, splices out HTML hidden by styling or comments and leaves a placeholder, folds confusable glyphs and flags look-alike hosts and exfiltration-shaped URLs, reporting each change as a warning or note. As a Claude Code plugin it applies these checks through hooks on prompts, tool input and tool output.

Written by ooruby from the README of agent-sanitizer 2.58.8.

Not claimed by its maker. Is this yours? Prove it and answer the findings

Why it's useful

Untrusted text can carry instructions hidden from people but read by models, and this strips or flags those hidden channels first.

What you could do with it

  1. 1Clean fetched web pages so HTML hidden with styling is cut out before your model reads the text.
  2. 2Install the Claude Code plugin so tool output in each session is cleaned of invisible characters.
  3. 3Use its credential matcher to find which environment variable names hold secrets before scrubbing them.

Written from its documentation: what it says it can do, not what our checks found.

ASagentDeveloper tools

Maintenance

Not measured

No release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.

Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured

Not yet tested
Command execution is bounded
inventory
node child_process (src/repo-scope.mjs:19)
synchronous shell execution (src/repo-scope.mjs:50)
node child_process (claude-hooks/lib/hook-io.mjs:11)
synchronous shell execution (claude-hooks/lib/hook-io.mjs:797)
An inventory of where the code starts another program, not a verdict on this row: whether each one runs a fixed program or whatever it is handed takes a reading by hand.

Published because it was found. A finding is information about where the limits are, not a verdict that the software is unsafe.

What this does not cover

  • ·Everything. Treat it as you would software from anywhere else.

Receipt history: every signed receipt for every version of this listing, and what changed between them.

In its maker's words

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.

Compare with

  • Acpxside by side
  • Fallowside by side
  • Vanguard Frontier Agenticside by side
Compare all 4

How far this has been checked

Static scanned

What it establishes
Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
What it does not
How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
Exactly what was read
Version 2.58.8, the file with digest sha512-j5wPW+EvPk3F8KUmu0hXdYDEjnNcPzrBr15lgeM10uSkAWcYhlZQTlyPgmyipGvnUDvyFeGw+T8NHAM+UKYCFQ==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
Authentication
Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
How the rungs work

Adding it

Run it with:

npx -y agent-sanitizer@2.58.8

Pinned to 2.58.8, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.

Where this came from

Registry
npm
Package
agent-sanitizer
Version read
2.58.8
Resolved
2026-10-09
Open the source(opens in a new tab)

Built from source, attested

npm publishes a signed statement that this exact package was built from the repository below, at this commit. It is verifiable without taking our word for it.

Repository
github.com/alexandermattturner/agent-sanitizer
Commit
875325f74dc8
Built by
github.com/actions/runner/github-hosted
Registry publish attestation
signed by npm · 2026-10-10
Checked
2026-10-10

The badge, if this is your listing

It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.

[![ooruby: static scanned](https://ooruby.com/api/badge/agent-sanitizer)](https://ooruby.com/market/agent-sanitizer)

About this listing

Kind
Agent
Category
Developer tools
Pricing
Free
Sandbox
No
Hosted
No
Updated
2026-10-08
Price
Free
Get it freeVisit maker
Rating
no reviews yet
0 want this so far
Sign in to vote

Sign in to watch this listing and hear when its version, rung or findings change.

Similar agents

All agents
OCagentDeveloper tools
3 findingsStatic scanned
Sign in with a ChatGPT account to use it under a Plus, Pro, Business, Edu or Enterprise plan, or use an API key with some extra setup. Separate options exist for code editors, a desktop app and the cloud-based Codex Web.

Openai Codex

openai
Free

Runs OpenAI's Codex coding agent locally on your computer from the command line.

71.3M installs/moApache-2.0
SKagentDeveloper tools
Clean scanStatic scanned
Skills come from GitHub repositories, given as owner and repository or as a full address, and you can try one without installing it. Updates can cover global skills, project skills or a single named skill.

Skills

rauchg
Free

Installs, finds, updates and removes agent skills across many coding agents from one command line.

38.3M installs/moMIT
ADagentDeveloper tools
Clean scanStatic scanned
It checks environment variables and reports the agent's ID, display name and session ID where one exists, with an opt-in process-tree check. A command line check answers by exit code.

Agent CLI Detector

ide
Free

Lets your JavaScript command line tool tell whether a coding agent is running it, and which one.

14M installs/moMIT

Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.