moralis-openapi-skill
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches an OpenAPI schema from the vendor's official GitHub repository (holon-run/uxc). This is a standard and expected configuration process using the author's infrastructure.
- [COMMAND_EXECUTION]: The skill instructs the agent to use the uxc utility to create command aliases and interact with the Moralis API. All command patterns are focused on the stated purpose of reading blockchain data.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes data from external blockchain APIs which may contain third-party content. * Ingestion points: Wallet history, token metadata, and swap data are retrieved via the moralis-openapi-cli (SKILL.md). * Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded in the API responses. * Capability inventory: The skill has command execution capabilities through the uxc CLI tool as documented in SKILL.md and references/usage-patterns.md. * Sanitization: No sanitization or validation of the retrieved JSON data is requested from the agent before processing.
Audit Metadata