helius-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 downloads a curated OpenAPI specification from the vendor's official GitHub repository (holon-run/uxc). This schema is used by the uxc tool to discover and execute API operations against Helius endpoints.
- [COMMAND_EXECUTION]: The instructions direct the agent to use the uxc CLI tool to set up authentication, create command aliases (link), and perform network operations. These are standard operations for this toolset.
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill ingests external data from the Helius Wallet API (api.helius.xyz), including wallet identities, balances, and transaction history (SKILL.md).
- Boundary markers: The skill provides instructions to the agent to focus on the JSON output envelope and parse specific stable fields (ok, kind, protocol, data, error) to maintain robustness.
- Capability inventory: The skill possesses the capability to execute shell commands via the uxc tool (SKILL.md, references/usage-patterns.md).
- Sanitization: No explicit sanitization or filtering of the remote API content is documented before the data is processed by the agent.
Audit Metadata