alchemy-openapi-skill
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches a curated OpenAPI JSON schema from a public GitHub repository (raw.githubusercontent.com) to define the structure of its API operations.
- [COMMAND_EXECUTION]: The skill uses the uxc CLI to manage credential bindings and perform network requests, which involves executing shell commands in the agent's environment.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes data retrieved from an external service. 1. Ingestion points: The skill reads JSON data from api.g.alchemy.com. 2. Boundary markers: There are no explicit instructions to the agent to ignore or delimit instructions potentially embedded within the pricing data. 3. Capability inventory: The skill's capabilities are restricted to network-based read operations via the uxc tool. 4. Sanitization: The skill does not define specific validation or sanitization logic for the API responses before they are presented to the agent.
Audit Metadata