skills/alinaqi/maggy/agent-teams/Gen Agent Trust Hub

agent-teams

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The team-lead agent reads and processes feature specification files from _project_specs/features/*.md to 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-lead agent can spawn new agents (TeamCreate) and manage tasks (TaskCreate), while implementation agents have access to Write, Edit, and Bash tools.
  • 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
Risk Level
SAFE
Analyzed
Jul 14, 2026, 04:18 PM
Security Audit — agent-trust-hub — agent-teams