Back to skill

Security audit

Maus HTML Summary

Security checks for vulnerabilities and agentic risk

Overview

This skill is an output-only HTML explainer template with no executable code, persistence, credential use, or hidden data movement.

Before installing, understand that the skill may be invoked automatically for article or transcript summarization tasks and will transform provided text into HTML. Avoid giving it sensitive source material unless you are comfortable with that content appearing in the generated summary.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill enables implicit invocation while advertising a broad, natural-language use case ('turn this article, transcript, or text into a playful, illustrated HTML explainer'). That can cause the agent to auto-select this skill for loosely related prompts and route arbitrary user content into HTML generation, increasing the chance of unintended execution paths, content injection into generated HTML, or invocation without clear user intent.

Content

No source excerpt is available for this finding.