team-live-ops

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows a structured orchestration pattern using the Task tool to delegate specific responsibilities to sub-agents.
  • [SAFE]: Includes a mandatory 'Ethics Review' phase (Phase 7) that checks the economy design against a local ethics policy, providing warnings if the policy is missing or if violations are detected.
  • [SAFE]: Implements manual checkpoints using AskUserQuestion, ensuring the user approves agent proposals before the pipeline proceeds to subsequent phases.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input via the season name/event description argument which is then passed to sub-agents.
  • Ingestion points: Primary argument [season name or event description].
  • Boundary markers: None explicitly defined in the orchestration prompt to separate user input from agent instructions.
  • Capability inventory: The orchestrator and its sub-agents have access to Bash, Write, Edit, and Read tools.
  • Sanitization: No explicit sanitization or validation of the event description is performed before delegation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 06:28 PM