smart-router-skill

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a central router script to execute specific workflow scripts based on user-provided arguments.
  • Evidence: router.sh executes scripts using bash "$SCRIPT_PATH" "$MISSION".
  • Mitigation: The script path and arguments are strictly validated. The character name must match a predefined whitelist (yoda, stark, sherlock), and the mission ID is restricted to the digits 1 or 2 using a regular expression. This prevents arbitrary command injection.
  • [SAFE]: The skill does not perform any network operations, access sensitive files, or attempt to persist across sessions.
  • [SAFE]: No prompt injection or obfuscation techniques were detected. The themed content, including mentions of 'bypassing protocols' in the Tony Stark workflow, is purely decorative and part of the character role-play output.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 07:08 PM