accept-task
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads and executes the latest version of the official CLI tool
@openant-ai/clifrom the NPM registry vianpx. - [COMMAND_EXECUTION]: The skill uses shell commands to interact with the OpenAnt platform for authentication, task retrieval, and task acceptance. These commands are limited to the vendor's specific toolset.
- [DATA_INGESTION]: The skill ingests external task data, including descriptions and metadata provided by other users on the platform. While this presents a surface for indirect prompt injection, the risk is mitigated by the structured nature of the CLI output and the lack of high-risk capabilities like arbitrary code evaluation on the returned data.
Audit Metadata