Skills
Navigate
skills/charlie947/agent-harness-starter/agent-harness-setup/Gen Agent Trust Hub

agent-harness-setup

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell scripts (scripts/setup.sh and scripts/seed-claude-md.sh) to manage file structures.
  • Evidence: SKILL.md explicitly calls for running bash skill/scripts/setup.sh to scaffold directories.
  • Risk Mitigation: The scripts are provided within the skill package, do not perform network operations, and use safe practices like set -euo pipefail and creating timestamped backups (.backup-YYYYMMDD-HHMMSS) before overwriting any user files. All logic is confined to the user's $HOME/.claude directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 10:41 AM
Security Audit — agent-trust-hub — agent-harness-setup