add-teams
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution: The skill uses the
Bashtool to executepa app add data-sourceandnpm run build. These operations are standard for Power Platform development and building project assets. The commands are used for their intended purpose within a development environment. - Indirect Prompt Injection: The skill is designed to read and update project files such as
memory-bank.mdand generated service definitions insrc/generated/services/. While reading external project files can theoretically introduce untrusted data into the agent's context, this is a standard requirement for development tasks to maintain state and inspect codebases.
Audit Metadata