practice-plan-creator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): The instructions are standard persona-setting guidelines. There are no attempts to bypass safety filters or override system constraints.
- [Data Exposure & Exfiltration] (SAFE): No commands for accessing sensitive files (~/.ssh, .env, etc.) or performing network requests were found.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not reference any external packages or scripts. It contains no executable code or shell commands.
- [Indirect Prompt Injection] (SAFE): Although the skill is designed to process user-provided sports context, it lacks any functional capabilities (like web browsing, file writing, or command execution) that could be exploited via malicious user input.
Audit Metadata