# Agent Sanitizer

> Fail-closed sanitization for tool inputs, tool outputs, and user prompts: invisible-Unicode/ANSI stripping, hidden-HTML splicing, exfil-URL detection, confusable normalization, and detect-secrets-backed secret redaction.

## Facts
- Page: https://tashan.sh/capability/plugin-alexandermattturner-agent-sanitizer-agent-sanitizer
- tashan id: plugin:alexandermattturner/agent-sanitizer/agent-sanitizer
- Source: https://github.com/AlexanderMattTurner/agent-sanitizer
- Type: plugin
- Category: security
- tashan score: 47.0 / 100
- Adoption: 13.0
- Upkeep: not measured
- Freshness: 100.0
- Evidence coverage: 59% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- GitHub stars: 2
- License: Apache-2.0
- Official: no

## Install

```sh
/plugin marketplace add AlexanderMattTurner/agent-sanitizer
/plugin install agent-sanitizer@agent-sanitizer
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-05 by tashan (https://tashan.sh) from public evidence. Scorer s5.