agent-teams
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The
team-leadagent reads and processes feature specification files from_project_specs/features/*.mdto determine the task structure and spawn sub-agents. This creates a surface where instructions embedded in those specification files could influence the orchestration logic. - Ingestion points:
team-lead.md(Responsibility 1: Read_project_specs/features/*.md). - Boundary markers: Absent; the instructions do not specify delimiters or constraints to prevent the agent from following instructions found within the specification data.
- Capability inventory: The
team-leadagent can spawn new agents (TeamCreate) and manage tasks (TaskCreate), while implementation agents have access toWrite,Edit, andBashtools. - Sanitization: Absent; the skill does not describe any validation or sanitization of the specification content before it is used to define team tasks.
Audit Metadata