next-issue@16.4.0
Autonomous issue harness driven by the Claude Agent SDK
AI security review
scanned · by lpm-firewall-aiThe manifest has no install lifecycle hook, and the flagged write is gated by the user-run init command and a chosen scope. The skills support the package’s documented issue-harness workflow.
Decision evidence
public snapshot- The manifest exposes a CLI and has no install, preinstall, or postinstall script.
- Skill installation is reached through the explicit init command.