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.mddirects 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