circleci-smarter-testing
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute specific CircleCI CLI commands, such as
circleci testsuite doctorandcircleci extension install testsuite. These are official vendor-provided tools used for their intended purpose of project configuration and diagnostics. - [INDIRECT_PROMPT_INJECTION]: The skill processes JSON output from the
circleci testsuite doctorcommand, specifically theaction_itemsandnext_stepsfields, to guide the setup process. While this represents a surface for ingesting tool-generated content, the source is a trusted local utility, and the interaction is restricted to project configuration tasks. - [SAFE]: The instructions include a specific security guardrail advising the agent and user never to put secrets in YAML files, instead recommending the use of secure environment variables and contexts.
Audit Metadata