minecraft-dev

Warn

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the minecraft-dev-cli tool using shell-style command patterns where user-supplied inputs are interpolated into flags (e.g., minecraft-dev-cli <tool> --key value). This pattern is susceptible to command injection if the agent does not properly sanitize or escape the values before execution.\n- [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data from Minecraft JAR files and decompiled Java source code.\n
  • Ingestion points: The skill reads external data via tools like analyze_mod_jar, decompile_mod_jar, and search_mod_code which process local mod JAR files.\n
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are provided to prevent the agent from obeying malicious instructions that might be present in decompiled code or JAR metadata.\n
  • Capability inventory: The skill allows the agent to execute shell commands via the CLI tool and perform filesystem operations related to JAR processing.\n
  • Sanitization: There is no evidence of content sanitization or validation performed on the data extracted from these untrusted sources before it is interpreted by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 25, 2026, 08:50 PM
Security Audit — agent-trust-hub — minecraft-dev