@passioncode-ai/fabric-agent-adapter@0.30.0
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 user-run CLI installs agent skills and its Claude plugin registers session hooks. This supports a warning for agent extension lifecycle risk, not a finding of malicious behavior.
Decision evidence
public snapshot- package.json exposes a CLI and has no install lifecycle hook.
- The CLI checks whether the Claude plugin is installed and selects a skills directory under the user’s home folder.
- When run, the CLI removes an existing destination when forced and copies the package’s skills there.
- The Claude plugin registers commands for stop and session-end events.
- Session hooks spool data only when Fabric advertises the required feature and the Fabric server is registered; on session end, the worker can release session claims.
- The agent setup requires an explicit CLI invocation or separate plugin installation.
- The inspected source shows no confirmed malicious behavior or unrelated network recipient.
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@0.30.0.
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@0.30.0 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.