go-test-effectiveness

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard Go toolchain commands, including go test, go test -race, and go test -cover. These operations are essential for the skill's primary function of validating Go code and are executed within the user's local repository environment.
  • [INDIRECT_PROMPT_INJECTION]: As a tool designed to analyze and design tests for user-provided Go code, the skill naturally processes external data. This creates an inherent attack surface for indirect prompt injection via malicious code comments or strings. The skill mitigates this by focusing on structural behavior and requiring the agent to use independent oracles and human-reviewed fixtures for validation rather than relying on the code under test itself.
  • [EXTERNAL_DOWNLOADS]: The skill suggests several well-known Go community libraries such as github.com/google/go-cmp, pgregory.net/rapid, go.uber.org/goleak, and Testcontainers-Go. It also mentions mutation testing tools like Gremlins and avito-tech/go-mutesting. These are established developer tools, and the instructions explicitly advise checking for maintenance and Go-version compatibility before adoption.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 08:17 PM