Back to skill

Security audit

Product Pricing Scraper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a basic public price-scraping helper with no hidden persistence or credential handling, but its documentation overstates what the included script actually does.

Install only if you want a lightweight helper for organizing already-scraped price data and guiding manual web extraction. Treat the advertised scraping, CSV, tracking, and currency-conversion features as incomplete, and ensure any scraping respects site terms, robots.txt, and permission boundaries.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The skill claims capabilities such as scraping major e-commerce sites, currency conversion, CSV output, and price tracking that are not actually implemented. This mismatch can mislead downstream agents or users into making decisions based on assumed functionality, and in security terms it obscures the real behavior and review surface of the skill.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding

The skill advertises and instructs use of network access and structured output generation, but it does not declare any explicit tool scope such as allowed-tools or permissions. Missing scope boundaries makes it easier for an agent runtime to over-grant capabilities or invoke this skill in broader contexts than intended, increasing the risk of unintended network access or file output behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The activation description is broad enough to match many generic shopping, pricing, or product-related prompts, which can cause the skill to trigger outside narrowly intended scraping use cases. Over-broad triggering increases the chance of unnecessary network activity, unintended data handling, or misuse in contexts where users did not explicitly request scraping.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The module docstring says 'Product pricing scraper' and the CLI description repeats that framing, implying the script performs scraping. However, the implementation explicitly says scraping must be done by an external web_fetch or browser tool and only ingests JSON from stdin.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest describes a skill that supports scraping Amazon, eBay, Walmart, and generic product pages, with price extraction and comparison. In this file, the code explicitly states it is a placeholder, instructs the user to use another tool for scraping, and merely reads pre-scraped JSON from stdin before formatting output.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.