MCP server exposing Telora product operations to Claude Code
Soft block: AI-agent control surface
Warn by default; block when configured. The installed commands are configured to run on Claude Code tool-use and prompt events across the user's projects.
AI security review
scanned · by lpm-firewall-ai
The manifest activates a postinstall hook that silently mutates global Claude Code event settings. This is unconsented install-time control-surface mutation, so the package should be blocked.
npm installation when both Telora hook binaries are available on PATH.
Impact
The installed commands are configured to run on Claude Code tool-use and prompt events across the user's projects.
Mechanism
scripts/postinstall.js adds command hooks to ~/.claude/settings.json under PostToolUse and UserPromptSubmit, then writes the file.
Policy narrative
During installation, the postinstall script checks for two Telora hook binaries. If both are present, it adds them as global Claude Code event handlers and writes the settings file without an installer consent step. Those handlers are configured to run on tool-use and prompt events across projects.
Avoid installing @telora/mcp-products@0.23.20. Remove it from direct dependencies and check your lockfile for transitive copies.
Choose an independently verified alternative or release. This report does not establish that other versions are safe.
If this version ran, check your AI agents' configuration and instruction files (the files this report lists) for changes you did not make, and remove them. This finding does not by itself establish malware intent.