reading-teacher

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: CRITICALCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The scripts generate_game.sh and generate_playground.sh use the eval command to process menu selections from the select command. While the current options are hardcoded, the use of eval on variable content is a poor security practice that could be exploited if the input sources were expanded.\n- [PROMPT_INJECTION] (LOW): The scripts accept a user-provided filename via read -p and use it to construct a file path without sanitization. This creates a surface for indirect prompt injection via path traversal.\n
  • Ingestion points: OUTPUT_FILE variable in both scripts/generate_game.sh and scripts/generate_playground.sh.\n
  • Boundary markers: None; the input is directly used in path construction.\n
  • Capability inventory: File system write access via cat redirection.\n
  • Sanitization: Absent; the scripts do not validate the filename or prevent the use of ../ sequences to write files outside the intended directories.
Recommendations
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 17, 2026, 05:28 PM