Auth Flow Planner
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and markdown templates. It does not perform any file system operations, network requests, or code execution.
- [PROMPT_INJECTION]: Analysis of the instructions found no attempts to bypass safety filters or override agent constraints. The skill acts on user-provided application descriptions which represents a surface for indirect injection; however, the lack of dangerous tool capabilities renders this surface harmless. Ingestion points: User prompt interaction; Boundary markers: Absent; Capability inventory: Limited to markdown text generation; Sanitization: Absent.
Audit Metadata