ClawHub
Back to skill

Security audit

Perplexity Search Skill

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Perplexity web-search skill that sends user search queries to Perplexity using the user’s own API key.

Install this only if you are comfortable sending search queries to Perplexity with your own API key. Avoid using secrets, regulated personal data, or confidential business information in queries, and monitor Perplexity usage because requests may consume paid quota.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill clearly requires environment access for `PERPLEXITY_API_KEY` and performs outbound network requests, but the manifest does not declare corresponding permissions. Even if the behavior is expected for a search skill, missing explicit permission declarations weakens security review and user consent by obscuring the skill's actual capabilities.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The README states the agent will automatically use this skill for web searches, but it does not clearly warn users that their search queries are sent to Perplexity, a third-party service. This can lead users to disclose sensitive prompts, internal data, or proprietary research terms without informed consent, creating a privacy and data-governance risk.

Missing User Warnings

Low
Confidence
79% confidence
Finding
The script sends the user's raw query to a third-party API, but the CLI output and flow do not provide an explicit privacy notice at runtime. In a search skill this is expected behavior, but it can still create a privacy issue if users enter sensitive data assuming the search happens locally.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.