ClawHub

Aviation Agent

Security checks across malware telemetry and agentic risk

Overview

The skill appears to fetch aviation weather from a narrow public source, but it is framed for pilot go/no-go decisions without enough safety scoping.

Review before installing. Use this only as an informational weather-decoding helper, not as a substitute for official preflight briefings, NOTAM/TFR checks, regulations, or pilot-in-command judgment. Confirm the skill declares and limits its external network access to aviationweather.gov.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill explicitly instructs use of a script that fetches live data from aviationweather.gov, which is a network capability, yet the skill metadata shown here does not declare any permissions. Undeclared network access weakens transparency and policy enforcement, and in an agent environment can allow data exfiltration or unreviewed external calls under the guise of normal skill operation.

Vague Triggers

Medium
Confidence
81% confidence
Finding
The trigger phrases are broad enough to match many common aviation or weather-related queries, including high-stakes questions like 'can I fly today.' Over-broad routing can cause the skill to activate unexpectedly and provide operational guidance in contexts where a narrower, safer workflow or stronger disclaimers would be more appropriate.

Missing User Warnings

High
Confidence
97% confidence
Finding
The skill advertises go/no-go decision support for pilots without a clear warning that outputs are advisory only and not a substitute for official FAA-approved briefing sources, current regulations, or pilot-in-command judgment. In an aviation context this is especially dangerous because users may over-trust concise AI summaries for flight safety decisions, increasing the risk of unsafe operations.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal