Agent Plugins Marketplace
← All plugins

block-invisible-unicode

v0.0.4

The mechanizable slice of prompt-injection defense, enforced at two points: at commit (the git hook, over staged changes) and at agent tool-use (over a tool call's arguments, as the agent writes) -- invisible and direction-override Unicode. Bidi controls make code read differently than it parses (Trojan Source, CVE-2021-42574); Unicode tag-block characters smuggle instructions that are invisible to a human reviewer but fully legible to the agent reading the file. Zero-width joiners and bidi marks (ZWJ/ZWNJ/LRM/RLM) are deliberately NOT matched -- they are legitimate in emoji sequences and in Persian, Arabic and Indic text -- so ordinary internationalised content passes; only the override/embed/isolate controls and the tag block, which have no honest use in a source tree, are blocked. Escape: 'pragma: allowlist invisible-unicode' on the same line. [Session-enforced via PreToolUse and Stop hooks; needs git and a Python 3.11+. PreToolUse judges the file a tool call would write; Stop re-reads what the turn actually left on disk, so a file written through a shell heredoc is judged too. With no working Python the hook exits 2; without git, fail-open clients allow silently. A gate that cannot reach a decision refuses rather than allowing one it never judged. Enforcement at every commit and in CI still needs chock installed in the repo.]

Claude Code1 Skill

By chock-coreLicense: Apache-2.02 GitHub starsUpdated 6 days ago

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 30, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install block-invisible-unicode for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install block-invisible-unicode-6@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/open-coder-ai/chock-copilot-plugins

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is claude/block-invisible-unicode/.

Plugin files

claude/block-invisible-unicode/
├── .claude-plugin/plugin.json
└── skills/block-invisible-unicode/SKILL.md

Included Skills1

block-invisible-unicodeskills/block-invisible-unicode/SKILL.md

The mechanizable slice of prompt-injection defense, enforced at two points: at commit (the git hook, over staged changes) and at agent tool-use (over a tool call's arguments, as the agent writes) -- invisible and direction-override Unicode. Bidi controls make code read differently than it parses (Trojan Source, CVE-2021-42574); Unicode tag-block characters smuggle instructions that are invisible to a human reviewer but fully legible to the agent reading the file. Zero-width joiners and bidi marks (ZWJ/ZWNJ/LRM/RLM) are deliberately NOT matched -- they are legitimate in emoji sequences and in Persian, Arabic and Indic text -- so ordinary internationalised content passes; only the override/embed/isolate controls and the tag block, which have no honest use in a source tree, are blocked. Escape: 'pragma: allowlist invisible-unicode' on the same line.

Plugin manifests1

claude/block-invisible-unicode/.claude-plugin/plugin.json
{
  "name": "block-invisible-unicode",
  "description": "The mechanizable slice of prompt-injection defense, enforced at two points: at commit (the git hook, over staged changes) and at agent tool-use (over a tool call's arguments, as the agent writes) -- invisible and direction-override Unicode. Bidi controls make code read differently than it parses (Trojan Source, CVE-2021-42574); Unicode tag-block characters smuggle instructions that are invisible to a human reviewer but fully legible to the agent reading the file. Zero-width joiners and bidi marks (ZWJ/ZWNJ/LRM/RLM) are deliberately NOT matched -- they are legitimate in emoji sequences and in Persian, Arabic and Indic text -- so ordinary internationalised content passes; only the override/embed/isolate controls and the tag block, which have no honest use in a source tree, are blocked. Escape: 'pragma: allowlist invisible-unicode' on the same line. [Session-enforced via PreToolUse and Stop hooks; needs git and a Python 3.11+. PreToolUse judges the file a tool call would write; Stop re-reads what the turn actually left on disk, so a file written through a shell heredoc is judged too. With no working Python the hook exits 2; without git, fail-open clients allow silently. A gate that cannot reach a decision refuses rather than allowing one it never judged. Enforcement at every commit and in CI still needs chock installed in the repo.]",
  "keywords": [
    "chock",
    "policy-as-code",
    "hook",
    "block",
    "{'control': 'asi01', 'coverage': 'partial', 'note': 'blocks the hidden-character slice of goal-hijack payloads a diff can show; semantic injection defense remains advisory (injection-defense, owasp-asi01-agent-goal-hijack)'}"
  ],
  "version": "0.0.4",
  "author": {
    "name": "chock-core"
  },
  "license": "Apache-2.0",
  "repository": "https://github.com/open-coder-ai/chock-catalog"
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[block-invisible-unicode on Agent Plugins Marketplace](https://pluginsmp.com/plugins/block-invisible-unicode-6)