ClawHub
Back to skill

Security audit

Tinyfish Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward TinyFish web-search helper with disclosed API-key use and outbound search queries.

Install only if you are comfortable providing a TinyFish API key and sending search queries, plus optional location and language parameters, to TinyFish. Avoid using it for confidential queries unless that matches your TinyFish account and data-handling expectations.

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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill invokes shell commands (bash, curl, and a helper script) but does not declare any permissions or allowed-tools scope. This creates an authorization gap where an agent runtime may permit broader shell execution than intended, increasing the chance of command execution beyond simple web search or of unsafe query handling in downstream scripts.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This code sends the provided query, and optionally location and language parameters, to an external API via curl. Although the script is clearly a search helper, it does not include any explicit user-facing notice at the point of transmission beyond the header comment, so users may not realize their input is being sent off-system.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.