ClawHub
Back to skill

Security audit

clawec-ozon-product-hot-ranking

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward ClawEC API helper for Ozon product ranking research, with disclosed API-key and network use.

Install only if you are comfortable giving the skill access to the ClawEC API using your CLAWEC_API_KEY. Prefer an environment variable over pasting keys into chat, review filter JSON before running the helper script, and treat returned product/business metrics as third-party API data.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill instructs use of shell via curl/bash examples and references a local script, but it declares no corresponding permissions or capability constraints. This creates a mismatch between documented behavior and the execution model, which can lead agents or platforms to invoke shell access without explicit authorization, increasing the risk of command execution, secret exposure, or unsafe parameter handling if user-controlled values are passed through.

Static analysis

No suspicious patterns detected.