MCP server exposing Telora product operations to Claude Code
Soft block: AI-agent control surface
Warn by default; block when configured. Claude Code may run the configured Telora commands on tool use and prompt submission without the user explicitly configuring those hooks.
AI security review
scanned · by lpm-firewall-ai
The manifest invokes a postinstall script that conditionally writes behavior-bearing hooks into the user's global Claude Code settings. This unconsented install-time mutation meets the ai_agent_control_hijack rule.
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 telora-ai-hook and telora-ai-human-hook are both on PATH.
Impact
Claude Code may run the configured Telora commands on tool use and prompt submission without the user explicitly configuring those hooks.
Mechanism
The postinstall script reads ~/.claude/settings.json, adds PostToolUse and UserPromptSubmit command hooks, and writes the settings file.
Policy narrative
During installation, if both Telora hook binaries are available on PATH, the package silently modifies Claude Code's global settings to run them on tool use and prompt submission. This is an unconsented install-time change to an AI-agent control surface.
Avoid installing @telora/mcp-products@0.23.29. 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.