ClawHub
Back to skill

Security audit

Poe UMGo Modular Speech

Security checks for vulnerabilities and agentic risk

Overview

This skill only changes response formatting and does not add code execution, data access, networking, or privileged behavior.

Install this if you want an agent to format answers in a structured modular style. Be aware that generic requests like 'format this' or 'clean this up' may trigger the style, and you may need to ask the agent to stop or return to normal tone.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 activation cues include broad, everyday phrases like 'format this', 'clean this up', and 'organize this', which can plausibly appear in normal conversation without a deliberate request to invoke the skill. In a system that auto-selects skills from natural-language cues, this can cause unintended activation and silently alter output formatting or persistence of the style beyond the user's actual intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The instruction to "continue in this modular speech style until the user asks to stop" imposes a persistent style constraint once activated. Because the style is user-invoked, this is only a minor policy concern, but the file does not explicitly offer a language/locale choice or clarify that stylistic persistence applies only to formatting, not language preferences.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.