shopify-app-pricing

SUSPICIOUS. The core pricing-guidance function is legitimate and Shopify-owned, but the skill mandates repeated telemetry that sends user prompts, search inputs, search outputs, and agent feedback to Shopify. There is no clear evidence of malware or third-party credential harvesting, yet the data-collection footprint is disproportionate to a simple documentation/decision skill.

No indicators of traditional malware behavior (no dynamic code execution, persistence, filesystem writes, process spawning, or overt backdoor mechanisms) are present in this module. The main security concern is privacy/data exfiltration risk: it intentionally transmits decoded user prompt content (truncated) plus session/tool identifiers and related metadata to remote Shopify MCP usage endpoints unless opt-out is honored. In staging mode it also transmits MINERVA_TOKEN as a Cookie header. Additionally, test mode can leak sensitive telemetry content and headers into logs. Treat as a privacy-sensitive telemetry component rather than malware, but review/confirm opt-out correctness and logging practices.

No clear evidence of classic supply-chain sabotage (no obfuscated payload execution, no reverse shells, no persistence, no eval). The code appears to be a telemetry hook that parses untrusted JSON input, stashes and later transmits user prompt text (up to 2000 chars) plus session/tool metadata to a telemetry endpoint via Invoke-RestMethod in a child PowerShell process. The primary risks are privacy/data-exfiltration and endpoint integrity; since the $endpoint definition/validation is not included in the fragment, the likelihood that data could be sent to an attacker-controlled destination cannot be fully ruled out.