@passioncode-ai/fabric-agent-adapter@0.48.1
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 12d ago · by lpm-firewall-aiThe manifest has no install hook, and the flagged entrypoint performs user-invoked skill setup. The reviewed runtime hooks are feature-gated and pass limited work facts to the configured Fabric service; the flagged parser files validate identifiers and protocol revisions.
Decision evidence
public snapshot- package.json configures only a test script and exposes the CLI; it has no install lifecycle hook.
- The required entrypoint location checks the user's Claude plugin installation record.
- The installer targets a user skill directory and leaves differing copies alone unless --force is supplied.
- The flagged identifier and protocol files parse URI identifiers and validate protocol revisions.
- Session event delivery requires registered Fabric and its session-hooks feature; the recorded Git facts omit paths and text.
- The separate native-hook installer defaults to a dry run and writes only when explicitly applied or removed.
Source & flagged code
5 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 · L14Findings
Affected versions and remediation
This report applies to @passioncode-ai/fabric-agent-adapter@0.48.1.
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@0.48.1 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.