serper

Security checks across malware telemetry and agentic risk

Overview

This web-search skill behaves as described, but users should know their searches go to Serper and result pages are fetched from third-party websites.

Install only if you are comfortable using a Serper API key and having search terms sent to Serper while result URLs are fetched from external sites. Avoid sensitive secrets, private internal URLs, or confidential investigations as queries, and treat extracted webpage text as untrusted research material.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
86% confidence
Finding
The README prominently advertises full-page scraping and query forwarding to Serper, but it does not clearly warn users that their search terms are sent to a third-party API and that the tool will fetch and extract content from external websites. This creates a transparency and privacy risk: users may unknowingly submit sensitive queries or trigger requests to untrusted sites, which is especially relevant in an agent/skill context where tools may be invoked indirectly.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill performs external search requests and then fetches full content from multiple third-party pages, yet the description provides no privacy warning or user-facing notice that queries and resulting page fetches will be sent to external services. This can expose sensitive user intent, local context, or proprietary research topics to Serper and destination websites, especially because the skill encourages broad content extraction rather than snippet-only retrieval.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal