ClawHub
Back to skill

Security audit

social-persona-switcher

Security checks for vulnerabilities and agentic risk

Overview

This is a simple humor-writing skill that rewrites a user’s sentence into several social personas and does not request sensitive access or run code.

Install this if you want a playful rewriting helper. Be aware it may activate on ordinary sentences more often than a narrowly invoked skill, and its humor/persona styles can be exaggerated or sarcastic, so review outputs before posting them publicly.

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
Confidence
96% confidence
Finding
The skill is configured to trigger on essentially any ordinary user sentence and common phrasing, rather than requiring an explicit invocation. This can cause unintended activation, hijack normal conversations, and override user intent by injecting persona-transformation behavior when the user did not ask for the skill.

Natural-Language Policy Violations

Low
Confidence
91% confidence
Finding
The skill automatically forces output to match the detected input language without asking the user, which can reduce user control and produce unwanted language selection in multilingual or ambiguous contexts. While not a severe security flaw, it can lead to confusing behavior, mishandling of user preferences, or accidental disclosure in the wrong language context.

Static analysis

No suspicious patterns detected.