setup-sui-contracts

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the runtime workflow to start from llms.txt and follow its links to package READMEs/catalogs (public web content fetched at runtime), which would be outsider-authored free text ingested into the agent’s LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs agents to fetch and follow the AI discovery entry point (https://raw.githubusercontent.com/OpenZeppelin/contracts-sui/main/llms.txt) and to query the OpenZeppelin MCP at runtime (https://mcp.openzeppelin.com/contracts/sui/mcp), both of which are runtime external data sources that an agent would fetch and use to drive its actions and decision-making.