ClawHub
Back to skill

Security audit

Ad Insight Hub Free

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed AdMapix API lookup helper with one narrow troubleshooting issue but no evidence of hidden, destructive, or unrelated behavior.

Install only if you are comfortable sending ad-search terms and app identifiers to AdMapix using your ADMAPIX_API_KEY. Avoid entering secrets or proprietary campaign details as search terms, and remove or ignore the ping troubleshooting instruction because it is unnecessary for rate-limit handling.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Intent-Code Divergence

Medium
Confidence
93% confidence
Finding
The error-handling section instructs the agent to execute system-level ping checks during API failures, even though the skill’s stated purpose is limited to AdMapix data queries. Expanding from a scoped HTTP API workflow into arbitrary host/network probing increases the chance of unauthorized environment reconnaissance and violates least-privilege expectations for a data lookup skill.

Context-Inappropriate Capability

Medium
Confidence
95% confidence
Finding
Telling the agent to perform ping-based connectivity tests for rate-limit or authorization errors grants behavior unrelated to the business function of ad-intelligence search. In an agent with exec access, this can normalize host probing and create an avenue for unintended network enumeration or policy bypass under the guise of troubleshooting.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The capability coverage section is excessively broad and fuzzy, listing many loosely related phrases without clear trigger boundaries. That ambiguity can cause unintended invocation or over-collection of user requests, which is risky in a skill that also has exec and remote API access.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill sends user-supplied query content to a third-party API but does not clearly disclose that user data will leave the local agent environment. Without an explicit data-sharing warning, users may provide sensitive competitive, campaign, or proprietary app information that is then transmitted externally without informed consent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.