minecraft-fabric-dev

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions are focused exclusively on legitimate Minecraft modding tasks such as source code analysis, documentation retrieval, and version porting.
  • [SAFE]: Network activity is restricted to syncing official Fabric and Baritone documentation via internal MCP tool calls.
  • [SAFE]: Data ingestion analysis (Category 8): The skill processes external JAR files and source code for analysis. While this presents a surface for indirect prompt injection, it is the primary purpose of the skill.
  • Ingestion points: JAR files via analyze_mod_jar and source code via analyze_mixin (SKILL.md).
  • Boundary markers: The instructions lack explicit delimitation for analyzed content, but the agent's role is strictly defined as an analyzer.
  • Capability inventory: Includes decompilation (decompile_minecraft_version), remapping (remap_mod_jar), and documentation syncing (sync_fabric_docs).
  • Sanitization: Not explicitly mentioned, but the workflow uses structured analysis tools rather than direct execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 12:55 PM