add-test

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): No shell commands, system calls, or arbitrary script executions were detected.
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill does not reference or attempt to download content from any external or untrusted URLs.
  • [DATA_EXFILTRATION] (SAFE): No network operations or patterns indicating the transfer of sensitive local data to external systems are present.
  • [PROMPT_INJECTION] (SAFE): The instructions are task-oriented and do not attempt to bypass safety filters or override the agent's core operational logic.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill identifies a data ingestion point via the Read tool for local files (SKILL.md). While boundary markers and sanitization are absent, the target file is expected documentation within the user's project, and the capability to generate test files is a low-risk text-generation task.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 04:21 AM