Hacktoberfest 2026: the issues maintainers tagged for October, open and beginner-friendly. Browse Hacktoberfest issues

Security considerations: tool text can contain characters nobody sees

Open Beginner friendly
  • Is something wrong?
#360 0 comments 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

Nobody has claimed this yet.

Assessment

Difficulty
1/5
Estimated time
1-3 hours
Newbie friendliness
72/100
Issue type
Documentation
Clarity
Clearly specified
Activity status
Active
Tech stack
markdown
Domain
documentation, security

Research direction

Read the existing security considerations and the related issues #11, #159, and #313 to find the right place for this note. Add a short, non-normative explanation of invisible Unicode characters in tool text and the suggested precautions for implementers. Done when the security considerations include the requested guidance without introducing a normative requirement.

Written by the indexing model from the issue text.

Description

This isn't a new attack, and it may be a minor thing, but I would like the security considerations to mention it so implementers of guardrails and agents don't forget it.

A tool's title, description and the strings inside its schemas can contain characters that take no space on screen but are still part of the text: Unicode tag characters (U+E0000 to U+E007F), which can spell out ASCII, zero-width characters, and bidirectional controls that reorder what a reader sees. A hidden instruction is no stronger than a visible one, but it gets past anything that only looks at what a person or a pattern matcher sees: a code review, a tool list in a UI, or a guardrail that matches keywords.

That matters most when something else registers tools on a page the site owner trusts, like a third-party script (#159). Tool names are already limited to ASCII, so they aren't affected, and a length limit (#73, #219) doesn't help, since a few hundred of these fit under any limit.

I work on a guardrail system myself, and the systems that run on ordinary machines with local models tend to depend on mechanical matching or on small models. That is because running a large model for both the agent and the guardrail makes inference too slow to use. Those are the systems where this is a real problem, since a small model or a matcher can be easier to confuse with text it can't see than a large one is. They should normalize text before they match on it, stripping or decoding these characters, and a host that shows a title or description to the user for approval shouldn't show something different from what it gives the model. So a short note for implementers would be enough. I'm not asking for a normative rule. Related: #11 and #313.

Dominant language
Bikeshed
Stars
4.7k
Forks
328
Avg merge
2d 15h
Merged PRs (30d)
16

Getting set up

This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from webmachinelearning/webmcp

All issues in webmachinelearning/webmcp

Similar issues

More Documentation issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.