# inspect_untrusted_text

Normalize untrusted text and detect common prompt-injection indicators

Agent View of the PolicyLayer registry record for `inspect_untrusted_text`. HTML page: https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/inspect-untrusted-text

## Facts

- Tool: `inspect_untrusted_text`
- Server: Project Guardian MCP (`1999azzar/project-guardian-mcp-server`) — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server.md
- Homepage: https://github.com/1999AZZAR/project-guardian-mcp-server
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "inspect_untrusted_text",
    "arguments": {}
  }
}
```

## Why inspect_untrusted_text is rated Low

This tool analyzes input text to identify security patterns but does not modify data, execute code, delete information, or trigger external operations. It is a read-only security analysis capability that examines content for malicious patterns. The low severity reflects that misuse would primarily affect analysis accuracy rather than system state or external consequences.

From the tool's own definition: "Tool performs text normalization and detection of prompt-injection indicators; the verb 'inspect' and 'detect' indicate passive analysis without data modification, deletion, or external execution. No side effects mentioned."

## Use case

AI agents call inspect_untrusted_text to retrieve information from Project Guardian MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Project Guardian MCP:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "inspect_untrusted_text": {}
  }
}
```

## Other tools on Project Guardian MCP (37)

- `cache_delete` — Destructive — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/cache-delete.md
- `delete_data` — Destructive — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/delete-data.md
- `delete_entity` — Destructive — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/delete-entity.md
- `delete_observation` — Destructive — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/delete-observation.md
- `delete_relation` — Destructive — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/delete-relation.md
- `close_ui` — Execute — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/close-ui.md
- `execute_sql` — Execute — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/execute-sql.md
- `initialize_memory` — Execute — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/initialize-memory.md
- `scan_container_image` — Execute — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/scan-container-image.md
- `start_ui` — Execute — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/start-ui.md
- `stop_ui` — Execute — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/stop-ui.md
- `analyze_git_changes` — Read — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/analyze-git-changes.md
- `cache_get` — Read — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/cache-get.md
- `cache_scan` — Read — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/cache-scan.md
- `export_data` — Read — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/export-data.md
- `get_file_context` — Read — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/get-file-context.md
- `get_project_guidance` — Read — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/get-project-guidance.md
- `get_session_context` — Read — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/get-session-context.md
- `get_timeline` — Read — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/get-timeline.md
- `list_harness_stores` — Read — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/list-harness-stores.md
- `open_node` — Read — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/open-node.md
- `query_data` — Read — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/query-data.md
- `read_graph` — Read — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/read-graph.md
- `read_graph_stream` — Read — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/read-graph-stream.md
- `scan_project_secrets` — Read — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/scan-project-secrets.md
- `search_nodes` — Read — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/search-nodes.md
- `sync_central_memory` — Read — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/sync-central-memory.md
- `add_observation` — Write — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/add-observation.md
- `cache_set` — Write — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/cache-set.md
- `create_entity` — Write — https://policylayer.com/tools/1999azzar-project-guardian-mcp-server/create-entity.md
- …and 7 more: https://policylayer.com/tools/1999azzar-project-guardian-mcp-server.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=1999azzar-project-guardian-mcp-server · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/1999azzar-project-guardian-mcp-server