Back to skill

Security audit

Image Analyzer Advisor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward image-analysis prompt with a small privacy caveat around image paths and URLs.

Installers should be aware that the skill may analyze local image paths or remote image URLs supplied in a request. Avoid using it with sensitive images, private internal URLs, signed links, or file paths you do not want repeated in the conversation.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger text is very broad and can activate on ordinary image-related requests, causing the skill to run in situations beyond the user's likely intent. Because the skill accepts image URLs and file paths, over-triggering increases the chance of unnecessary remote fetches, unintended processing of sensitive local/remote resources, and privacy leakage through automatic analysis behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly supports remote image URLs and instructs the agent to always include the image path/URL in the response, but it provides no warning about the privacy and security implications. This can expose sensitive local paths, internal URLs, signed links, or user-provided remote resources in model output, and can also encourage unsafe retrieval of attacker-controlled URLs.

Content

No source excerpt is available for this finding.