long-running-orchestrator

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a manual state-management system using local markdown files (e.g., ledger/current.md) to maintain context across sessions. This is a standard architectural pattern for long-running workflows.
  • [COMMAND_EXECUTION]: The skill references the execution of a local utility script bash scripts/checkpoint.sh. This script is intended to automate progress saving as part of the core functionality.
  • [DATA_EXPOSURE]: The skill references a configuration file located at ~/.claude-harnesses/cost-ledger.json to monitor tool usage costs. Access to this specific path is within the scope of the skill's stated cost-guard functionality and does not involve sensitive user credentials like SSH or AWS keys.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 11:35 AM
Security Audit — agent-trust-hub — long-running-orchestrator