@theronap/agnoclast-mcp@0.9.149
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-aiThis is not malicious under the lifecycle policy because there is no registry-install trigger and the risky configuration is reached by explicit commands. It remains suspicious because it sets persistent AI-agent hooks and automatically transmits session-derived data once configured.
Decision evidence
public snapshot- The explicit install command wires multiple AI editors and records their capabilities.
- The Claude setup path installs session hooks that invoke capture automatically.
- The capture hook reads session transcript content and posts a derived record to the vendor API.
- The Antigravity adapter writes a launchd watcher and shell script that invokes a remote package tag.
- package.json has no preinstall, install, or postinstall lifecycle hook.
- Configuration changes require explicit setup or install commands; the launchd plist is written but not loaded.
- The capture path redacts transcript content before its fallback upload.
Source & flagged code
6 flaggedThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
lib/capture.mjsView on unpkgPackage source references weak cryptographic algorithms.
lib/capture.mjsView on unpkg · L1Findings
Affected versions and remediation
This report applies to @theronap/agnoclast-mcp@0.9.149.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.149 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.