MCP server exposing Telora product operations to Claude Code
Soft block: AI-agent control surface
Warn by default; block when configured. The registered commands gain automatic execution opportunities across Claude Code sessions.
AI security review
scanned · by lpm-firewall-ai
Source confirms an unconsented npm postinstall mutation of global Claude Code hook settings. This meets the blocking policy for broad AI-agent control-surface changes.
Installing the package when both Telora hook executables are on PATH.
Impact
The registered commands gain automatic execution opportunities across Claude Code sessions.
Mechanism
The postinstall script writes those executable paths into the global PostToolUse and UserPromptSubmit hook lists without an interactive consent step.
Policy narrative
The npm postinstall hook checks for two Telora executables, then adds them to global Claude Code hooks that run on tool-use and prompt events. This automatically changes a broad agent control surface during installation without asking the user.
Avoid installing @telora/mcp-products@0.23.2. 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.