NYC

microsoft-guide

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to ingest and process a large external file (NET-Microservices-Architecture.md), which represents a potential surface for embedded instructions.
  • Ingestion points: The file NET-Microservices-Architecture.md located in the skill directory.
  • Boundary markers: Absent; the instructions do not specify delimiters or guardrails to distinguish the guide's content from system instructions.
  • Capability inventory: The skill utilizes grep for searching file content but does not involve network operations, file writing, or administrative shell access.
  • Sanitization: Absent; the content is searched and referenced directly without escaping or validation logic.
  • [Command Execution] (SAFE): The instruction to 'Use Grep' is a standard tool-use directive for agents to search local data and does not constitute unauthorized or malicious command execution in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:47 PM