ClawHub
Back to skill

Security audit

Cheapcharts

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed CheapCharts deal-lookup skill that makes web/API requests for movie and TV pricing without showing credential access, persistence, or destructive behavior.

Install this if you are comfortable with the agent sending movie or TV title queries to CheapCharts, and occasionally IMDb for Movies Anywhere-style compatibility checks. Treat the unofficial DetailData endpoint as potentially unstable, but I did not find evidence of credential use, local data access, hidden persistence, or destructive actions.

SkillSpector

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
93% confidence
Finding
The recipes explicitly instruct use of an unofficial internal CheapCharts endpoint and third-party IMDb scraping beyond the stated public-API-only scope. This expands the skill's effective capabilities to undocumented and potentially unstable or unauthorized data sources, increasing legal, reliability, and abuse risk if an agent follows the guidance automatically.

Context-Inappropriate Capability

Medium
Confidence
91% confidence
Finding
The IMDb scraping recipe directs the agent to fetch and parse a third-party website unrelated to the core CheapCharts API workflow. In an agent skill, adding unrelated scraping broadens data exfiltration and compliance risk, and may cause the agent to make network requests users did not expect from a simple price-lookup capability.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The document contains extensive external network-call recipes but does not provide user-facing warning that the skill will contact third-party services. While network access is expected for this kind of skill, the lack of disclosure reduces transparency and can create privacy or policy issues if user queries are sent to external services without clear notice.

Static analysis

No suspicious patterns detected.