minecraft-modding

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill instructions create an indirect prompt injection surface where a malicious repository could influence agent behavior.\n
  • Ingestion points: references/core-project-context.md directs the agent to read repository instructions, build files (root/module), and mod metadata.\n
  • Boundary markers: There are no specific instructions or delimiters to mark project-derived content as untrusted or to ignore embedded instructions.\n
  • Capability inventory: The skill is intended for a development environment where the agent can modify source code and interact with build systems (Gradle).\n
  • Sanitization: No sanitization or validation of the repository content is performed before it is added to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 05:05 AM
Security Audit — agent-trust-hub — minecraft-modding