golang-testing
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary purpose is to provide instructional content and code patterns for Golang testing, following industry standards.
- [COMMAND_EXECUTION]: Provides examples of using the Go toolchain and docker-compose for running tests and managing local development fixtures.
- [EXTERNAL_DOWNLOADS]: Mentions and suggests the installation of well-known Go libraries like testify, goleak, and clockwork from standard public repositories.
- [PROMPT_INJECTION]: The skill is configured to analyze and process user-provided source code to generate tests, which represents an indirect prompt injection surface.
- Ingestion points: User-supplied Go code enters the agent context via file reads or direct prompt input.
- Boundary markers: No specific boundary delimiters are defined to separate user code from the agent's internal instructions.
- Capability inventory: The agent has permissions to edit files and execute the Go toolchain via allowed-tools configuration.
- Sanitization: No sanitization or safety checks for the content of processed user code are implemented in the skill instructions.
Audit Metadata