ClawHub

oversize-baggage

Security checks across malware telemetry and agentic risk

Overview

This travel-search skill is generally coherent, but it needs review because it tells the agent to install an unpinned global third-party CLI automatically before running searches.

Review before installing. Use this only if you are comfortable with an agent installing @fly-ai/flyai-cli globally and sending travel search details to flyai/Fliggy; safer use would be to manually verify and install the CLI first, then run searches with user-approved parameters.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Intent-Code Divergence

Medium
Confidence
97% confidence
Finding
The skill explicitly says agents must never invent CLI parameters and may only use flags listed in the parameter table, but later instructs use of `--journey-type 1`, which is not documented there. This inconsistency can cause agents to ignore their own safety/validation rules, issue unsupported commands, or normalize use of undocumented flags that may have unintended behavior in the installed CLI.

Missing User Warnings

Medium
Confidence
99% confidence
Finding
The skill mandates installing a global npm package (`npm i -g @fly-ai/flyai-cli`) whenever the binary is missing, without user consent, provenance verification, or sandboxing guidance. That creates a supply-chain and arbitrary code execution risk because global package installation runs untrusted install scripts and modifies the host environment.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal