Back to skill

Security audit

Monitor Buying Consultant

Security checks for vulnerabilities and agentic risk

Overview

This is a pure instruction-based monitor buying guide with no code execution, persistence, or credential access, though users should note it does include named product suggestions despite claiming to be brand-neutral.

Install this only if you want the agent to guide monitor purchases and potentially name specific models. Treat product suggestions as research starting points, verify current specs, prices, warranty, and availability yourself, and be aware that the skill asks for location and hardware details to tailor advice.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (4)

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest markets the skill as brand-neutral, but the instructions later require recommending specific real monitor models by region. This creates a policy-integrity mismatch that can mislead users about neutrality and opens the door to covert product steering, affiliate-style influence, or undisclosed commercial bias under the guise of impartial advice.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill explicitly says it will not recommend specific brands, then later mandates suggesting real products and models. Contradictory instructions like this can be exploited to mask promotional behavior, confuse auditors, and erode user trust because the user is told the consultation is independent while the workflow ultimately steers them toward named products.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file includes activation examples such as "help me choose a monitor" and "best monitor for me," which are broad natural-language phrases rather than tightly scoped invocation triggers. Although the surrounding section provides some scope and negative examples, these phrases remain vague enough to match routine conversation and could cause unintended skill activation in systems that rely on phrase matching.

Content

No source excerpt is available for this finding.