sui-move-security
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and review Sui Move code, design records, and repository instructions, which serve as external ingestion points. While the skill primarily provides guidance for the agent's reasoning, the ingestion of untrusted code for review creates a surface for indirect prompt injection. \n
- Ingestion points: Target repository instructions, accepted design records, and Move source code referenced in the skill body. \n
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the analyzed code. \n
- Capability inventory: The skill configuration does not include any executable tools, subprocess calls, or network capabilities. \n
- Sanitization: There is no evidence of sanitization or filtering for the external code content processed during a review.
Audit Metadata