maui-current-apis

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by instructing the agent to parse external .csproj project files.
  • Ingestion points: Reading TargetFramework and PackageReference from project files as outlined in the reasoning framework.
  • Boundary markers: None; the agent is not guided to ignore or isolate instructions found within the XML content.
  • Capability inventory: The skill is used by agents with capabilities to generate and modify source code.
  • Sanitization: No validation or sanitization process for the ingested project data is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 12:07 AM