@theronap/agnoclast-mcp@0.9.243
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-aiSource inspection found no npm install hook or concrete attack behavior. The flagged agent configuration and persistence behaviors are tied to CLI management or require separate user activation.
Decision evidence
public snapshot- package.json exposes the CLI and lists release, promote, and rollback scripts; the inspected manifest shows no npm lifecycle hook.
- The Codex and Cursor adapters describe their integration scope and skip wiring when no token is supplied.
- Setup requires a supplied token and is reached through the explicit CLI setup command.
- The skills command manages package skills in detected Claude and Codex directories; uninstall is an explicit CLI command that removes local integration configuration.
- Transcript lookup searches session files under Claude project directories.
- Antigravity writes local artifacts, but its source says a user must load the launch agent to activate the watcher and notes a local-checkout dependency.
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@0.9.243.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.243 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.