The Agent Skills Directory

[Prompt Injection] (SAFE): The instructions define a clear persona and architectural principles without including patterns designed to override agent safety or extract system prompts.- [Data Exposure & Exfiltration] (SAFE): There are no commands or instructions that access sensitive files or perform network operations.- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not download or execute any external packages or scripts.- [Persistence & Privilege Escalation] (SAFE): No mechanisms for maintaining access or acquiring elevated permissions were found.- [Indirect Prompt Injection] (LOW): While the skill is designed to process user input about testing, it lacks any executable capabilities (file writes, network access, or command execution) that could be leveraged by an indirect injection attack.

testing-automation