MCP server exposing Telora product operations to Claude Code
Soft block: AI-agent control surface
Warn by default; block when configured. The registered commands are configured to run on subsequent prompt and tool events, changing Claude Code behavior globally for that user.
AI security review
scanned · by lpm-firewall-ai
The postinstall hook automatically writes behavior-bearing commands into global Claude settings without a consent gate. The separate interactive setup and connector actions do not guard this lifecycle mutation.
Package installation when both Telora hook binaries are available on PATH.
Impact
The registered commands are configured to run on subsequent prompt and tool events, changing Claude Code behavior globally for that user.
Mechanism
The installer adds hook entries to the global Claude settings file and writes the modified configuration.
Policy narrative
The package’s automatic postinstall conditionally discovers two Telora executables, adds them to global Claude prompt and tool hooks, and writes the settings without asking the installer. This changes agent behavior beyond the package’s own runtime. The inspected package does not establish what those external hook executables do, so the finding is the unconsented global control-surface mutation.
Avoid installing @telora/mcp-products@0.23.4. 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.