goal-setter

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for the agent to behave as a 'Goal Setter,' converting user requests into structured objectives with evidence and stop conditions. No signs of prompt injection or malicious overrides were found.
  • [SAFE]: The Python script scripts/validate_goal_length.py is a utility tool for counting characters and UTF-16 code units. It does not perform network operations, access sensitive files, or execute arbitrary code. It is used strictly for length validation.
  • [SAFE]: The skill mentions spawning subagents (spawn_agent) and creating threads (create_thread), which are platform-native mechanisms for task delegation and parallelism. These are used as intended for autonomous workflows without bypassing safety controls.
  • [SAFE]: No hardcoded credentials, sensitive path accesses, or unauthorized external downloads were detected. The skill operates within the expected development environment of the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 02:45 PM
Security Audit — agent-trust-hub — goal-setter