ClawHub

Reveyes Skill

Security checks across malware telemetry and agentic risk

Overview

This skill is a focused Amazon review fetcher that uses a declared Reveyes API key and helper script without hidden or unrelated behavior.

Install only if you trust Reveyes and the reveyes Python package. Treat REVEYES_API_KEY as a secret, avoid committing it to dotfiles or config, rotate it if exposed, and keep page counts small because the service uses credits per page.

SkillSpector

By NVIDIA
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
91% confidence
Finding
The skill declares use of an environment secret (`REVEYES_API_KEY`) and instructs execution of a local Python script, but does not declare explicit permissions for secret access or code execution. This creates a capability/permission mismatch that can cause the runtime to grant broader access implicitly or make security review miss that the skill can invoke code using sensitive credentials.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal