@theronap/agnoclast-mcp@0.9.278
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe package has no install hooks or automatic persistence activation. The flagged credential flow and editor configuration changes are limited to the stated Agnoclast integration and user-triggered setup or tool requests.
Decision evidence
public snapshot- The manifest has no install lifecycle hooks; it exposes an explicit CLI and declares only release, promote, and rollback scripts.
- Setup and cross-editor install are dispatched only when the user runs those commands.
- The confidential-session proof and seat-token exchange occur for a tool request naming a confidential brain and use the Agnoclast API flow.
- The Antigravity adapter writes its watcher artifacts when wired but does not load the launch agent.
- The CLI reads environment variables, accesses local configuration and credentials, and makes network requests as part of its MCP and setup functions.
- Antigravity’s generated launch agent watches local application state and can run a sync after a user activates it.
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@0.9.278.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.278 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.