testing-principles
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to identify and run shell commands for starting services, performing health checks, and executing tests based on the project's existing configuration. This is a functional requirement for verifying software behavior in end-to-end scenarios.\n- [INDIRECT_PROMPT_INJECTION]: The skill functions by ingesting and acting upon untrusted data from the project environment, such as configuration files and design documents.\n
- Ingestion points: Project configuration files, test scripts, design documentation, and skeleton annotations found within the repository.\n
- Boundary markers: The instructions do not specify the use of delimiters to isolate project data from the instruction context.\n
- Capability inventory: The skill allows for the execution of shell commands for service management and test runners, as well as interaction with the project's database engine.\n
- Sanitization: There are no instructions for the agent to sanitize or validate the content of repository files before interpreting them as part of the testing workflow.
Audit Metadata