create-context-tests
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references official documentation at
docs.getnao.iofor evaluation guidelines and identifies the Anthropic API endpoint (api.anthropic.com) within a troubleshooting step. These are recognized as well-known or vendor-affiliated resources. - [COMMAND_EXECUTION]: The instructions utilize the
naoCLI tool suite (nao test,nao chat) for running evaluations and managing the agent's local environment. These tools are consistent with the vendor's primary functionality. - [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided information such as dashboard queries and metric definitions to generate YAML test files. This represents an ingestion surface for potentially untrusted data; however, the skill explicitly requires a manual validation step ("Have the user validate") before the generated content is used, which acts as a security boundary.
Audit Metadata