agent-team-builder

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill processes user-provided task descriptions which are then passed to sub-agents. This creates a surface for instructions embedded in data to override agent behavior.\n
  • Ingestion points: User input collected during Phase 1 in SKILL.md.\n
  • Boundary markers: The skill lacks explicit markers or instructions for agents to treat input as data only.\n
  • Capability inventory: Uses tools like Task, TeamCreate, and SendMessage to manage sub-agents.\n
  • Sanitization: No sanitization of user input is performed before interpolation into agent prompts.\n- Dynamic Execution (LOW): The skill generates agent prompts at runtime based on patterns and user input. This is a standard and intended function for this type of orchestration skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 02:23 PM