ClawHub
Back to skill

Security audit

Tarot from Univoice

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only reflective tarot skill with no code execution, data access, persistence, or hidden behavior, though its activation wording is broader than ideal.

Install only if you want tarot-style reflective responses. Be aware that broad prompts about feeling stuck or wanting clarity may invoke this framing even without explicitly asking for tarot.

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
  • 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
92% confidence
Finding

The activation rules are broad enough to match generic requests for clarity, guidance, or support when the user did not ask for tarot specifically. That can cause the agent to steer ordinary emotional-support conversations into a symbolic divination frame, which may be inappropriate, unwanted, or confusing for vulnerable users despite the skill’s otherwise careful boundaries.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.