@passioncode-ai/fabric-agent-adapter@0.24.0
Create Fabric-compatible agents, run them as always-alive local services with dashboards (fabric-service/0.1), and adapt existing projects to the Fabric Agent Contract. This package is the installer CLI.
AI Security Review
scanned 21d ago · by lpm-firewall-aiThe package has no npm install hook, but its Claude plugin configures automatic session hooks that conditionally report project metadata to Fabric. This is a first-party agent extension capability, so warn without blocking.
Decision evidence
public snapshot- package.json defines a test script and CLI entrypoint, with no install lifecycle hook.
- The installer reads Claude’s plugin registry to check whether this plugin is installed; it copies skills to agent directories when the CLI runs.
- The plugin registers commands that run at session start, turn stop, and session end.
- The stop and end hooks require a running Fabric that advertises the session-hook feature and has the Fabric server registered.
- The worker sends a commit identifier and change counts through the existing Fabric session; it does not send file paths or diff text.
- The manifest does not define an npm install-time execution hook.
- The inspected hook flow is conditional and sends limited project metadata through the registered Fabric service.
Source & flagged code
6 flaggedManifest-trigger-reachable source writes behavior-bearing configuration into a user or project AI-agent control surface.
bin/fabric-agent-adapter.jsView on unpkgPackage source references dynamic require/import behavior.
bin/fabric-agent-adapter.jsView on unpkg · L13Findings
Affected versions and remediation
This report applies to @passioncode-ai/fabric-agent-adapter@0.24.0.
See all versions of @passioncode-ai/fabric-agent-adapter for other recorded verdicts.
- Review the evidence and your use of @passioncode-ai/fabric-agent-adapter@0.24.0 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.