ClawHub
Back to skill

Security audit

Tarot Spreads

Security checks for vulnerabilities and agentic risk

Overview

This is a simple tarot-reading guidance skill with clear entertainment/reflection boundaries and no code, persistence, credential use, or external access.

Install this only if you want tarot-style entertainment and reflection responses. Do not rely on it for medical, legal, financial, safety, or crisis decisions, and be aware it may sometimes trigger on broad card/spread/reflection wording even when tarot was not explicitly intended.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The phrase "use when the user asks for tarot, card reading, spread, or a symbolic mirror for a situation" includes "spread" and especially "a symbolic mirror for a situation," which are ambiguous and not tightly scoped to tarot requests. These broad terms can overlap with ordinary conversation and make activation boundaries unclear.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The keyword list includes broad terms like "card spread" that may match non-tarot contexts, and the file does not provide negative examples or exclusion conditions. Because this is a markdown skill description, unclear trigger scope can lead to accidental activation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.