ClawHub
Back to skill

Security audit

pangolinfo-amazon-listing-optimization

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a coherent Amazon listing workflow, but it tells the agent to directly read an API key from the environment, which requires user review before installation.

Review this skill before installing. It appears focused on Amazon listing optimization and has no executable payload, but only use it in an environment where you are comfortable with the agent being instructed to access the Pangolinfo API key. Prefer a setup where credentials are handled by the MCP/tool configuration and are never printed, summarized, or exposed in chat.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Context-Inappropriate Capability

Medium
Confidence
92% confidence
Finding
The skill instructs the agent to access `PANGOLINFO_API_KEY` from environment/config even though listing optimization does not require credential-handling logic inside the prompt itself. Embedding secret-access instructions in skill content expands the skill's privilege scope and normalizes access to sensitive credentials from untrusted prompt material, which can lead to unintended secret exposure or misuse in adjacent agent implementations.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly tells the agent to read an API key from an environment variable without any boundary stating that secrets must remain inaccessible to prompt-controlled logic. In a hostile-skill analysis context, that is dangerous because prompt content should not direct credential access; doing so increases the chance that an agent with broad capabilities may fetch or disclose secrets beyond the user's intent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.