agent-goal-planner

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of a set of instructions defining an agent persona and methodology for complex planning. No malicious patterns, suspicious code, or security vulnerabilities were identified.
  • [PROMPT_INJECTION]: The instructions are focused on providing a framework for task decomposition and planning. There are no attempts to override safety filters, extract system prompts, or disregard instructions.
  • [EXTERNAL_DOWNLOADS]: The skill does not reference or download any external packages, scripts, or remote resources.
  • [DATA_EXFILTRATION]: No sensitive file access or unauthorized network operations are present. The tool call examples use local Model Context Protocol (MCP) definitions for orchestration and memory.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 04:32 PM