run-acceptance-tests
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill directs the agent to run
go testcommands. Given this is the primary intended use for testing, the severity is rated as LOW. - [PROMPT_INJECTION] (LOW): The skill exhibits an Indirect Prompt Injection surface (Category 8) because test names are interpolated into shell commands without sanitization. 1. Ingestion points: User-provided test names. 2. Boundary markers: None. 3. Capability inventory: Shell execution of
go test. 4. Sanitization: None mentioned in the instructions.
Audit Metadata