Google Reviews Pain Detector

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it scrapes review pages, scores sales leads, and only writes to the lead list when the user passes an explicit save flag.

Install only if you are comfortable with automated review-site scraping and with the local Scrapling dependency it imports. Run without `--save` first, inspect the scored leads, and back up the Master Lead List before allowing the script to append HOT leads.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill documentation advertises a `--save` mode that appends HOT-tagged leads back to a master list, but it does not warn users that this operation modifies persistent data. In an agent setting, undocumented write behavior increases the risk of unintended data corruption, duplicate entries, or silent alteration of a shared lead source, especially when users may assume the tool is read-only scraping/analysis.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The script can append automatically derived entries into a persistent master lead list when invoked with --save, with no confirmation prompt, dry-run default, backup, or transaction safety. In a skill context that processes untrusted scraped data and may run in bulk mode, this can silently corrupt or pollute internal business records with inaccurate, duplicated, or attacker-influenced content.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal