@passioncode-ai/fabric-agent-adapter@0.25.0
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 scanner’s flagged CLI location only reads Claude’s plugin registry, and the npm manifest has no install hook. The Claude plugin does add guarded automatic session behavior, so this is a warning for a first-party agent extension capability rather than a verified attack.
Decision evidence
public snapshot- The manifest exposes an explicit CLI and has only a test script; it defines no npm install hook.
- The flagged CLI location reads Claude’s installed-plugin registry; it does not write agent configuration.
- The CLI copies skills into the selected skills directory and skips existing installs unless forced.
- The Claude plugin registers session hooks that run on session events.
- Those hooks spool data only when Fabric is running, advertises the session-hook feature, and has a registered MCP server.
- The worker uses that registered command to send session observations containing commit and change counts, and can release the session’s claim at session end.
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@0.25.0.
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@0.25.0 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.