ClawHub
Back to skill

Security audit

test-search

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed web-search skill, but the packaged artifact appears incomplete because it references a script that is not included.

Install only if you intend to send search queries to iFlytek ONE SEARCH and are comfortable providing an XFYUN_API_PASSWORD. Avoid searching for secrets, private personal data, or confidential business material. Also verify or add the missing scripts/search.py implementation before expecting the skill to work.

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
  • 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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill documentation describes use of a third-party search API and notes that full page text may be returned, but it does not clearly warn users that their search queries and retrieved content are transmitted to and processed by an external provider. This creates a privacy and data-handling risk, especially if users search for sensitive, proprietary, or personal information under the assumption the data remains local to the agent environment.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.