Back to skill

Security audit

Welsh

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Welsh writing-style skill with no code execution, data access, persistence, or hidden behavior.

Install this if you want casual, natural-sounding Welsh. For formal, academic, official, or Welsh-only output, explicitly ask for that register because the skill otherwise nudges responses toward conversational Welsh with some English mixing.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The description mandates producing Welsh that is informal and non-robotic, which is a language/locale style constraint presented as a default rather than a user choice. This can violate language policy expectations when users may want formal Welsh or a different register unless the skill explicitly offers opt-in or choice.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The file says to 'lean casual' unless explicitly formal, imposing a default language register on all outputs. Because the skill does not clearly offer the user an opt-in choice of tone or formality, this is a natural-language policy concern under the language/locale rule.

Static analysis

No suspicious patterns detected.