The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references information and resources from trusted sources, including the official Sui documentation (docs.sui.io) and the vendor's own repository (github.com/MystenLabs/sui-stack-hello-world).
[INDIRECT_PROMPT_INJECTION]: The skill contains ingestion points for external data that could influence agent behavior.
Ingestion points: External documentation queried via an MCP server (https://sui.mcp.kapa.ai) and live blockchain events/transaction effects via gRPC streaming.
Boundary markers: None specified for the external data ingestion.
Capability inventory: The skill utilizes powerful CLI commands including sui client publish, sui client upgrade, and sui client call (SKILL.md).
Sanitization: No explicit sanitization or validation of the external content is mentioned.
Analysis: Given the data sources are official Sui infrastructure and well-known AI services, this represents standard development practices and is considered safe.
[COMMAND_EXECUTION]: The skill instructs the user to execute standard Sui CLI commands (sui client publish, sui client upgrade, sui start) for package management and local network operations. These are appropriate for the skill's stated purpose.

sui-publish