MCP server exposing Telora product operations to Claude Code
Soft block: AI-agent control surface
Warn by default; block when configured. The commands run automatically during Claude Code tool use and prompt submission, creating an unconsented AI-agent control surface.
AI security review
scanned · by lpm-firewall-ai
The automatic postinstall hook modifies Claude Code's global settings to register commands that run on tool use and prompt submission. This is an unconsented install-time mutation of an AI-agent control surface.
Static reason
High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review; source fingerprint signature matched known malicious package; routed for review; previous stored version diff introduced dangerous source
Trigger
Package installation when both telora-ai-hook and telora-ai-human-hook are on PATH.
Impact
The commands run automatically during Claude Code tool use and prompt submission, creating an unconsented AI-agent control surface.
Mechanism
The postinstall script inserts the binaries into PostToolUse and UserPromptSubmit hooks, then writes ~/.claude/settings.json.
Policy narrative
During installation, if both Telora hook binaries are available on PATH, the package adds them to Claude Code's PostToolUse and UserPromptSubmit hooks and writes the global settings file. This enables automatic command execution in future Claude Code sessions without an install-time consent prompt.
Avoid installing @telora/mcp-products@0.23.22. 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.