MCP server exposing Telora product operations to Claude Code
Soft block: AI-agent control surface
Warn by default; block when configured. Those commands run as Claude Code hooks, changing agent behavior without the user's explicit consent.
AI security review
scanned · by lpm-firewall-ai
The default postinstall hook modifies Claude Code's global settings to register commands that run on tool use and prompt submission, without user consent. This is an install-time AI-agent control-surface mutation.
Package installation, if both Telora hook binaries are on PATH.
Impact
Those commands run as Claude Code hooks, changing agent behavior without the user's explicit consent.
Mechanism
The postinstall script edits ~/.claude/settings.json to register commands for PostToolUse and UserPromptSubmit.
Policy narrative
On installation, if both Telora hook binaries are available on PATH, the package adds them to Claude Code's global PostToolUse and UserPromptSubmit hooks and writes the settings file without asking. This is an install-time mutation of an AI-agent control surface.
Avoid installing @telora/mcp-products@0.23.23. 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.