instar@1.3.1410
Coherence infrastructure for self-evolving AI agents — on the Claude Code or Codex subscription you already have.
AI Security Review
scanned 1d ago · by lpm-firewall-aiThis warrants a warning because the update migration removes permission prompts for agent requests and adds broad tool grants. The behavior is limited to existing Claude project settings, and the inspected credential flow uses Anthropic’s OAuth API.
Decision evidence
public snapshot- After an app update, the updater runs the CLI migration for its configured project directory.
- The migration changes settings only for Claude Code projects with an existing settings file, then writes the patched settings.
- The migration adds a project hook for every permission request; the generated hook returns an allow decision, including on timeout.
- It also adds Bash, file, task, and web tools to the project’s allowed tools.
- The inspected credential flow reads Claude credentials from local storage and sends the token to Anthropic’s OAuth API for quota polling.
- QuotaManager delegates quota checks to its migrator, passing current usage percentages.
Source & flagged code
17 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgPackage source references child process execution.
dist/threadline/PipeSessionSpawner.jsView on unpkg · L15Package source references shell execution.
Findings
Affected versions and remediation
This report applies to instar@1.3.1410.
See all versions of instar for other recorded verdicts.
- Review the evidence and your use of instar@1.3.1410 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.