agent-goal-planner
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes external task strings which creates a surface for indirect prompt injection.\n
- Ingestion points: The
taskparameter in themcp__claude-flow__task_orchestratetool call within SKILL.md.\n - Boundary markers: Absent; there are no delimiters or instructions to ignore embedded commands for the external task data.\n
- Capability inventory: Task orchestration via
mcp__claude-flow__task_orchestrate, agent swarm management viamcp__claude-flow__swarm_init, and data persistence viamcp__claude-flow__memory_usage(all defined in SKILL.md).\n - Sanitization: Absent; no escaping or validation of external input is described.\n- No Code (SAFE): No executable scripts (Python, JavaScript, Shell) or package dependencies were detected in the skill package, limiting the execution-based attack surface.
Audit Metadata