@theronap/agnoclast-mcp@0.9.253
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 15d ago · by lpm-firewall-aiSource inspection found no malicious behavior. The flagged configuration changes are tied to explicit setup or removal commands, and the Antigravity watcher is not activated by the adapter itself.
Decision evidence
public snapshot- The package manifest declares no install lifecycle hook; its scripts are release, promotion, and rollback commands.
- Setup, installation, and removal run only when the caller selects those CLI commands; setup requires a token.
- The Antigravity adapter writes a script and launch plist but says to load the watcher separately; its script depends on a local development checkout.
- Skill synchronization uses the configured token with the Cortex service and installs skills in Claude Code or Codex directories.
- Calendar tools send supplied event details to the Cortex service; the helper code validates and formats event data.
- The inspected entry points and dependency files show ordinary schema and protocol-library exports, with no malicious payload behavior identified.
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@0.9.253.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.253 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.