skills/dojoengine/book/dojo-system/Gen Agent Trust Hub

dojo-system

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill serves as a development guide for the Dojo framework, providing standard Cairo code snippets for smart contract systems. It does not include any executable scripts or binary files within the skill package.
  • [INDIRECT_PROMPT_INJECTION]: As a code generation tool, the skill processes user-provided descriptions (e.g., 'Create a system for player movement') to generate code. While this presents a standard surface for indirect prompt injection common to all LLM-based assistants, there are no specific vulnerabilities or malicious instructions embedded in the provided templates. The severity is low and inherent to the intended use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 03:19 AM