always-ask-next
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats or malicious patterns were identified during the analysis of this skill. The skill's primary function is to modify the agent's conversational flow to be more interactive.
- [PROMPT_INJECTION]: While the skill uses strong imperative language such as "Mandatory Rule" and "must always be followed without exception," these instructions are strictly confined to the agent's operational workflow (asking for user input before finishing). They do not attempt to bypass safety guidelines or system constraints.
- [COMMAND_EXECUTION]: The README files provide PowerShell and Bash commands for the user to create local directory structures for custom prompts (e.g., in VS Code's AppData or Library folders). These are benign configuration steps for the user and are not executed automatically by the skill.
- [DATA_EXFILTRATION]: The skill does not perform any network operations or access sensitive file paths. It relies on a standard interaction tool (
AskUserQuestion) to present options to the user within the existing chat interface.
Audit Metadata