ClawHub
Back to skill

Security audit

APIpie AI

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed APIpie AI connector skill that uses OOMOL's oo CLI, with no evidence of hidden or malicious behavior.

Install this only if you want the agent to use APIpie AI through an OOMOL-connected account. Review any chat or embedding payload before approval, because those calls can transmit text externally and may consume APIpie or OOMOL credits.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill description says to use this skill for ANY APIpie AI request and instead of calling the API directly, which is an overly broad trigger that can cause the agent to invoke the skill for loosely related tasks without sufficient user intent verification. Because the skill includes write-capable actions such as chat completion and embedding creation, unintended invocation can lead to unnecessary external data transmission, unexpected costs, or bypass of safer task-specific handling.

VirusTotal

48/48 vendors flagged this skill as clean.

View on VirusTotal