practice
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for a coaching and educational use case. It does not include scripts, executables, or commands.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user input (goals, level, time budget) to generate exercises.
- Ingestion points: User-provided goal and context in
SKILL.md. - Boundary markers: Absent.
- Capability inventory: No tools or scripts are defined or used.
- Sanitization: None.
Audit Metadata