@theronap/agnoclast-mcp@0.9.216
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 25d ago · by lpm-firewall-aiSource inspection found no install lifecycle hook or concrete attack behavior. The flagged configuration writes are package-specific integration actions invoked through the CLI, and the capture path submits data to Cortex.
Decision evidence
public snapshot- package.json defines a CLI entrypoint and release, promote, and rollback scripts, with no install lifecycle hook.
- The bin entrypoint performs editor wiring only when the explicit install command is invoked.
- The Antigravity adapter writes its named sync script and launch agent as part of editor setup.
- Codex and Cursor adapters describe their integration boundaries; Cursor capture does not inject sibling-session context.
- Setup accepts a token argument, skills target Claude and Codex directories, and uninstall supports dry-run and backups.
- Capture posts collected ingest data to the configured Cortex base; the reviewed source shows no unrelated recipient.
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@0.9.216.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.216 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.