# No prompt markup such as <IMPORTANT> or <system>

**Tags such as <IMPORTANT>, <system> or <instructions>, and chat-template tokens such as [INST] or <|im_start|>, address the model directly and are the signature of published tool-poisoning attacks; describe the tool instead.**

Check `sec-instruction-markup` · Poisoning and hidden text · default severity: blocking · rubric 2.1.0. Last verified against Anthropic connector pre-submission checklist on 2026-11-18.

## What fails

Tags such as <IMPORTANT>, <system> or <instructions>, and chat-template tokens such as [INST] or <|im_start|>, are how published tool-poisoning attacks address the model directly.

## The rule

> Describe what the tool does, and don’t tell Claude how to behave.

Source: [Anthropic connector pre-submission checklist](https://claude.com/docs/connectors/building/review-criteria#avoid-prompt-injection-patterns)

## How to fix it

Remove the markup and describe only what the tool does.

1. Remove prompt-style tags and chat-template tokens from all metadata.
2. Rewrite the content as a plain description of what the tool does.
3. Add a CI test.

A CI test that fails when the pattern comes back:

### TypeScript (node:test)

```js
// tools-list.test.mjs: run `node --test` after saving the answer with
// npx @modelcontextprotocol/inspector --cli <server> --method tools/list > tools.json
import assert from 'node:assert/strict';
import { readFileSync } from 'node:fs';
import { test } from 'node:test';

const answer = JSON.parse(readFileSync('tools.json', 'utf8'));
const tools = answer.tools ?? answer.result?.tools ?? answer;

// Every string and every key in a tool, with its path.
function* strings(value, path) {
  if (typeof value === 'string') yield [path, value];
  else if (value && typeof value === 'object')
    for (const [k, v] of Object.entries(value)) {
      yield [`${path}.${k} (key)`, k];
      yield* strings(v, `${path}.${k}`);
    }
}

const PATTERN = /<\/?(important|system|instructions?|assistant)\b|\[\/?INST\]|<\|im_(start|end)\|>/i;

test('no prompt markup', () => {
  const hits = [];
  for (const tool of tools) for (const [path, text] of strings(tool, tool.name)) if (PATTERN.test(text)) hits.push(path);
  assert.deepEqual(hits, [], 'prompt markup addresses the model instead of describing the tool');
});
```

### Python (pytest)

```python
# test_tools_list.py: run `pytest` after saving the answer with
# npx @modelcontextprotocol/inspector --cli <server> --method tools/list > tools.json
import json
import re

with open("tools.json", encoding="utf-8") as f:
    answer = json.load(f)
tools = answer.get("tools") or answer.get("result", {}).get("tools") if isinstance(answer, dict) else answer


def strings(value, path):
    """Every string and every key in a tool, with its path."""
    if isinstance(value, str):
        yield path, value
    elif isinstance(value, dict):
        for k, v in value.items():
            yield f"{path}.{k} (key)", k
            yield from strings(v, f"{path}.{k}")
    elif isinstance(value, list):
        for i, v in enumerate(value):
            yield from strings(v, f"{path}.{i}")


PATTERN = re.compile(r"(?i)</?(important|system|instructions?|assistant)\b|\[/?INST\]|<\|im_(start|end)\|>")


def test_no_prompt_markup():
    hits = [path for tool in tools for path, text in strings(tool, tool["name"]) if PATTERN.search(text)]
    assert hits == [], "prompt markup addresses the model instead of describing the tool"
```

## Questions

### We use <IMPORTANT> to stress a real constraint. Is that wrong?

Yes: state the constraint plainly ("Requires a project ID"). Anthropic asks descriptions to describe what the tool does, not tell Claude how to behave.

### Where did this pattern come from?

Security researchers published tool-poisoning examples in 2025 that used <IMPORTANT> blocks to make models read files and leak them.

## Related checks

- [No wording that overrides instructions or hides actions from the user](https://isokron.ai/mcp-check/checks/sec-instruction-phrases)
- [No HTML comments in metadata](https://isokron.ai/mcp-check/checks/sec-html-comment)
- [Metadata does not seek secrets or local files](https://isokron.ai/mcp-check/checks/sec-secret-seeking)
- [Tool poisoning and hidden text](https://isokron.ai/mcp-check/checks/security)

Counts toward: Poisoning and hidden text, Anthropic connector directory, OpenAI plugin directory.

Rubric: https://isokron.ai/mcp-check/rubric

Check your tool list: https://isokron.ai/mcp-check
