@theronap/cortex-mcp@0.9.146
Renamed to @theronap/agnoclast-mcp — use that. Existing installs switch themselves to the new name on next start.
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThe package has dangerous agent-extension capabilities and session-data transmission, but they are activated by explicit user commands and are aligned with the package's integration function. No npm install lifecycle hook, covert execution path, or concrete malicious chain was found.
Decision evidence
public snapshot- The explicit install command wires MCP entries, hooks, and permissions into detected AI-editor configurations.
- A stop hook reads session transcripts and posts derived content or a fallback transcript to the Agnoclast API.
- The Antigravity adapter writes a launchd plist and a script that invokes this package through npx at a moving stable tag.
- The package can add allow rules for its MCP tools, reducing prompts for those capabilities.
- package.json has no preinstall, install, or postinstall lifecycle hook.
- The configuration and hook changes are reached through explicit setup or install commands, not package installation.
- The launchd artifact is not loaded by the package; its code tells the user to load it manually.
- No obfuscated loader, eval-style execution, credential harvesting, or unrelated exfiltration path was found.
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/cortex-mcp@0.9.146.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.146 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.