Back to skill

Security audit

UI ROI Audit

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only UI audit skill with clear scope and no hidden code, persistence, credential use, or external execution behavior.

Install this when you want a structured, source-cited audit of a page, checkout, form, or task workflow. Provide only the page content, screenshot, URL, and business metrics you are comfortable sharing; the skill does not need credentials or broad local file access.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The instruction to load the module "for every task-driven interface" is very broad and lacks clear boundaries or exclusion conditions. Because this is a markdown file and SQP-1 applies, the trigger language could cause unintended invocation across many interfaces beyond the intended conversion-page usability-audit context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The routing examples switch between Polish and English requests, but the document does not explain whether the skill supports multiple languages by design or how language selection is determined. Because policy violations include forcing or implying a language/locale without clear opt-in, this mixed-language presentation creates ambiguity about the language behavior users should expect.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file includes example prompts such as "Why doesn't this product page convert?" and "tell me what to fix first," which are natural phrases a user might say outside an intentional skill invocation context. The README does not provide narrower activation constraints, exclusion conditions, or a clearly bounded trigger scope to reduce accidental matching.

Content

No source excerpt is available for this finding.