go-testing-with-testify
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted files such as source code, tests, and configuration files which could contain malicious instructions intended to manipulate the agent's behavior.
- Ingestion points: The workflow involves reading
go.mod, implementation files, test files, and fixtures (defined inSKILL.md). - Boundary markers: While it instructs identifying environment constraints, there are no explicit instructions to ignore or sanitize instructions embedded in source comments or string literals.
- Capability inventory: The skill utilizes shell command execution via
go testto validate behavior (defined inSKILL.md). - Sanitization: The instructions recommend narrow test targeting (e.g., using
-run '^TestName$') and manual inspection of failures, which serves as a basic mitigation against accidental execution of malicious code. - [COMMAND_EXECUTION]: The skill guides the agent to execute shell commands to run and diagnose Go tests.
- Evidence:
SKILL.mdandreferences/suite-and-parallelism.mdcontain specific instructions for runninggo testwith various flags like-race,-count,-shuffle, and-runto validate behavior and triage flakes.
Audit Metadata