device-guidance-v1-0-3
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill is designed to ingest and process data from an external source (a SharePoint list via the 'Get Employee Assets' tool). If the content retrieved from this tool contains malicious instructions, the agent could potentially act on them.
- Ingestion points: Data enters the agent's context through the
Get Employee Assetstool as described inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when presenting or processing the retrieved asset data.
- Capability inventory: The skill maps user-selected letters to internal SharePoint Item IDs and captures user-provided 'additional requirements' (like RAM or hard drive capacity) for inclusion in device requests.
- Sanitization: There is no evidence of explicit sanitization or validation of the data returned by the tool before it is presented to the user or used in follow-up actions.
Audit Metadata