tw-edu-classroom-culture
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local Python script ('scripts/generate_classroom.py') to process user inputs and generate educational Word documents.
- [PROMPT_INJECTION]: Identified a surface for indirect prompt injection where user-supplied strings are used as command-line arguments. 1. Ingestion points: User input for '--grade' and '--challenge' parameters in SKILL.md. 2. Boundary markers: Absent; input is interpolated directly into the Bash command. 3. Capability inventory: Access to 'Bash', 'Read', and 'Write' tools. 4. Sanitization: No explicit sanitization or escaping of these inputs is present in the provided scripts or instructions.
- [SAFE]: No obfuscation, hardcoded credentials, or suspicious network activities were detected. The skill's operations are consistent with its educational purpose.
Audit Metadata