@theronap/agnoclast-mcp@0.9.200
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-aiThe manifest has no npm install lifecycle hook, and the flagged assistant configuration behavior is reached through explicit CLI operations. The inspected source supports the package's stated assistant integration and capture functions without establishing a concrete attack.
Decision evidence
public snapshot- package.json exposes a CLI and lists release, promote, and rollback scripts, with no npm install lifecycle hook.
- Codex's adapter documents supported hook events and configures integration behavior.
- Cursor's adapter describes capture behavior and says it does not inject sibling-session context at prompt time.
- Setup uses assistant configuration paths and is reached through an explicit CLI command.
- Skills target the Claude and Codex skill directories.
- The flagged uninstall location identifies assistant configuration paths; its caller is the explicit uninstall/remove command, and its JSON edit filters managed MCP entries.
- Working-file lookup reads Claude project transcript files for a supplied session identifier.
- Antigravity writes its sync script and launch agent artifacts; its plist sets RunAtLoad to false.
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@0.9.200.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.200 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.