Metis · Data Guardian — Probe Tool Result
probe_tool_resultExamine external content for injection patterns before adding to agent context. Detects and reports suspicious patterns to prevent malicious input.
Instructions
M5.7.1 — Probe external tool result for injection patterns.
Call this before inserting any externally-sourced content into agent context:
web scrapes, RSS items, PDF extracts, YouTube transcripts, GitHub readmes.
Args:
content: The external content to probe.
source_label: Human-readable label for logging (e.g., "PubMed abstract", "RSS item").
Returns:
JSON with {probed_content, flagged, patterns_found}.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | ||
| source_label | No |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |