@theronap/agnoclast-mcp@0.9.232
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 19d ago · by lpm-firewall-aiSource inspection found no package install hook or concrete attack behavior. The flagged agent configuration and persistence indicators correspond to explicit integration and removal commands, while capture sends data to the package’s configured Cortex service using a wired token.
Decision evidence
public snapshot- package.json exposes a CLI and lists release, promotion, and rollback scripts; it has no install lifecycle hook.
- Setup and cross-editor installation run through explicit CLI commands. Setup requires a supplied token before wiring the assistant.
- The inspected editor and skill locations describe local integrations. The Codex and Cursor adapters do not inject prompt-time context; transcript lookup is keyed to the current session.
- Uninstall runs only through its CLI command and removes managed entries and matching package-owned launch agents.
- Antigravity setup writes a watcher artifact, but its launch configuration disables run-at-load and its source says activation requires an explicit launch command.
- Capture requires a wired token and sends its ingest body through the configured Cortex service, whose canonical endpoint is agnoclast.com.
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@0.9.232.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.232 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.