ClawHub
Back to skill

Security audit

Api Free

Security checks across malware telemetry and agentic risk

Overview

This appears to be an API reference skill, but it asks for broad command execution despite saying it is documentation-only.

Review before installing. This skill is likely intended as API documentation, but because it grants command execution and includes runnable API examples, users should ensure their agent will not run curl commands or use real API keys without explicit confirmation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Intent-Code Divergence

Medium
Confidence
91% confidence
Finding
The skill repeatedly claims it is documentation-only and will not execute user requests, but later instructs the agent to perform operations and return execution results. This mismatch can cause an agent or user to over-trust the skill as passive reference material when it is actually framed to drive actions, increasing the risk of unintended command execution or unsafe handling of user input.

Context-Inappropriate Capability

Medium
Confidence
95% confidence
Finding
The skill declares the exec tool even though its stated purpose is only to provide API reference documentation and not perform requests. Granting execution capability unnecessarily expands the attack surface: prompt-influenced shell commands such as head/sed/curl examples could be operationalized by an agent, enabling local command execution or outbound requests despite the documentation-only claim.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.