Runs OpenAI's Codex coding agent locally on your computer from the command line.
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
- Clean fetched web pages so HTML hidden with styling is cut out before your model reads the text.
- Install the Claude Code plugin so tool output in each session is cleaned of invisible characters.
- Use 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.
Maintenance
Not measuredNo 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
- 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
Compare all 4How 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.
Adding it
Run it with:
npx -y agent-sanitizer@2.58.8Pinned 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
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.
[](https://ooruby.com/market/agent-sanitizer)About this listing
- Kind
- Agent
- Category
- Developer tools
- Pricing
- Free
- Sandbox
- No
- Hosted
- No
- Updated
- 2026-10-08
Similar agents
All agentsVerification 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.