ClawHub
Back to skill

Security audit

volcengine-web-search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Volcengine web search helper, with expected third-party search queries and credential use for authentication.

Install only if you are comfortable sending search queries to Volcengine and using Volcengine or VeFaaS credentials in the agent environment. Use scoped credentials where possible and do not search for confidential text, secrets, or private internal content.

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
  • 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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill explicitly documents access to environment variables for authentication, but it does not declare any tool scope or permission boundaries. That omission can cause the runtime to grant broader capabilities than reviewers expect, making secret access less visible and reducing defense-in-depth around credential handling.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The function sends the caller-provided query directly to an external Volcengine web search API, which means any user input may leave the local trust boundary. In a search skill this behavior is expected, but the lack of user-facing disclosure, consent, or data-sensitivity checks can expose secrets, personal data, or proprietary prompts if upstream components pass sensitive text into the query.

Static analysis

No suspicious patterns detected.