ClawHub
Back to skill

Security audit

Perplexity Web Search

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed web-search helper that sends search queries to Perplexity and does not include bundled code, persistence, or hidden behavior.

Install only if you are comfortable with search queries being sent to Perplexity under your own API key and account terms. Avoid putting secrets, private documents, or sensitive personal data into web_search queries.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description is broadly phrased to activate for common actions like 'searching the web,' 'looking up information,' and 'fetching URL content,' which can cause it to be invoked in many unrelated contexts. Overly broad routing increases the chance that sensitive user prompts or internal task context are sent to an external provider unnecessarily, creating privacy, data handling, and policy-boundary risks even though the skill itself is not overtly malicious.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.