ClawHub
Back to skill

Security audit

shopify-research

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a Shopify research helper, but its bundled API script is broader than the Shopify-only purpose and can call arbitrary Crawlora endpoints with arbitrary POST bodies.

Review this skill before installing if you want strict Shopify-only behavior. It requires a Crawlora API key and sends requests to Crawlora; the documented use is public Shopify storefront research, but the included helper can call other Crawlora endpoints unless the agent or user voluntarily stays within the Shopify paths.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
96% confidence
Finding
The helper is explicitly documented and implemented as a generic Crawlora client, with examples for Amazon, YouTube, and Google endpoints that are unrelated to the stated Shopify-research purpose. In an agent skill context, this broadens the capability surface from store-specific research to arbitrary third-party API access, enabling misuse, policy bypass, or unexpected data retrieval beyond what users and operators would reasonably expect.

Context-Inappropriate Capability

Medium
Confidence
98% confidence
Finding
The code accepts an arbitrary path argument and appends it directly to the API base, permitting invocation of any Crawlora endpoint the key is authorized to access. In this skill, that means the implementation materially exceeds the declared Shopify auditing scope and can be repurposed as a general external data access primitive, increasing the risk of unauthorized or unintended operations.

External Transmission

Medium
Category
Data Exfiltration
Content
curl -fsS -G "${auth[@]}" "${qs[@]}" "${base}${path}"
else
  [ -n "$body" ] || body="${rest[0]:-{}}"
  curl -fsS -X "$method" "${auth[@]}" \
    -H "Content-Type: application/json" -d "$body" "${base}${path}"
fi
Confidence
83% confidence
Finding
curl -fsS -X "$method" "${auth[@]}" \ -H "Content-Type: application/json" -d

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:27