domain-researcher
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill documentation describes the use of 'npx chatdomain', which initiates the download and execution of a package from the NPM registry. While mentioned as a usage example, this represents a pattern of executing remote code at runtime.
- [EXTERNAL_DOWNLOADS]: The agent is instructed to use 'curl' to interact with the external domain 'chatdomain.ai' for checking availability and pricing of domain names.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data returned from external API endpoints, which could potentially contain instructions aimed at influencing agent behavior.
- Ingestion points: External data is ingested from 'https://chatdomain.ai/api/check' and 'https://chatdomain.ai/api/prices' during the domain research workflow.
- Boundary markers: The skill does not define explicit delimiters or warnings to ignore instructions that might be embedded in the API responses.
- Capability inventory: The agent has the capability to perform network requests via 'curl' and is instructed to manage multiple agent tasks in parallel.
- Sanitization: There is no evidence of sanitization or validation of the content returned from the external API.
Audit Metadata