@theronap/agnoclast-mcp@0.9.245
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 16d ago · by lpm-firewall-aiThe manifest has no install lifecycle hook, and the inspected configuration changes are reached through explicit CLI commands. The persistence hint is a watcher artifact that does not run at load and requires separate activation; the inspected login flow uses browser approval and the configured Cortex service.
Decision evidence
public snapshot- package.json defines the executable entrypoint and contains no npm lifecycle hooks.
- Setup and install are explicit CLI commands; their configuration changes run through those user-invoked paths.
- Editor adapters write package-specific MCP entries and skills; uninstall removes managed entries and supports a dry run.
- The Antigravity adapter writes a watcher configuration, but it does not run at load and requires a separate command to activate.
- Login uses a browser approval flow, sends its device code to the configured Cortex service, and passes the approved token to setup.
- The working-files module locates the current session transcript and tracks files touched during that session.
Source & flagged code
6 flaggedPackage source references weak cryptographic algorithms.
lib/capture.mjsView on unpkg · L1Findings
Affected versions and remediation
This report applies to @theronap/agnoclast-mcp@0.9.245.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.245 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.