fitness-program
Pass
Audited by Gen Agent Trust Hub on Jul 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a structured multi-agent workflow for fitness planning. It uses a local workspace (
_workspace/) for data sharing between specialized agents (architect, guide, linker, builder) and exhibits no malicious behaviors such as credential theft or unauthorized network communication. - [PROMPT_INJECTION]: The skill includes an indirect prompt injection surface as it ingests user-provided fitness programs for analysis.
- Ingestion points: User-provided program files are copied to
_workspace/01_program_design.mdfor processing by the agent team. - Boundary markers: None explicitly defined in the workflow instructions.
- Capability inventory: File read/write operations within the local workspace, inter-agent communication via
SendMessage, and task management. - Sanitization: No specific content validation is described for ingested files. However, the specialized roles of the agents and lack of access to system commands or external network tools mitigate potential risks.
Audit Metadata