arena

Pass

Audited by Gen Agent Trust Hub on Nov 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates a process where a parent agent spawns multiple subagents (candidates) and then reads their outputs 'end to end' for judging and merging. This creates a surface where adversarial instructions within a candidate's output could influence the parent agent's logic.
  • Ingestion points: SKILL.md Phase D ('Read every candidate end to end before picking').
  • Boundary markers: Absent. No delimiters or 'ignore embedded instructions' warnings are specified for the evaluation of candidate artifacts.
  • Capability inventory: The skill orchestrates multiple agents via /swarm and performs file operations via git and /tmp paths.
  • Sanitization: Absent. The candidate output is read and processed directly without verification or filtering.
  • [COMMAND_EXECUTION]: The skill relies on shell-based tools and internal framework commands for environment setup and agent management.
  • Evidence: Uses git worktree for branch-based isolation and the /swarm command for parallel subagent execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 17, 2026, 09:14 AM