learning-badge-system
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Prompt Injection] (LOW): The skill is susceptible to indirect prompt injection (Category 8) because it ingests untrusted user input via the 'topic' and 'educational_level' parameters and reflects them in its output without sanitization or boundary markers. 1. Ingestion points: 'topic' and 'educational_level' in skill.py. 2. Boundary markers: Absent. 3. Capability inventory: The skill has no dangerous capabilities such as file writes, network calls, or command execution. 4. Sanitization: Absent.
- [Safe] (SAFE): No evidence of hardcoded credentials, obfuscation, or remote code execution was detected. The path manipulation for the framework import is standard for local development.
Audit Metadata