Back to skill

Security audit

Let Fate Decide

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed creative tie-breaker that draws tarot cards locally and does not show hidden data access, persistence, or unsafe execution.

Install this only if you want occasional tarot-style randomness for ambiguous, low-stakes planning. Do not rely on it for security, production, data-loss, financial, legal, or other high-impact decisions, and opt out when you want deterministic reasoning.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (4)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
90% confidence
Finding

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

Content

Scanner excerpt · SKILL.md (reported line 88)May include surrounding context.

md
## Rationalizations to Reject

- "The cards said to, so I must" → Cards inform direction, they don't override safety or correctness
- "This reading justifies my pre-existing preference" → Be honest if the reading challenges your instinct
- "I'll keep drawing until I get what I want" → One draw per decision point; accept the reading

Instruction Override

High
Category
Prompt Injection
Confidence
90% confidence
Finding

This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 88)May include surrounding context.

md
## Rationalizations to Reject

- "The cards said to, so I must" → Cards inform direction, they don't override safety or correctness
- "This reading justifies my pre-existing preference" → Be honest if the reading challenges your instinct
- "I'll keep drawing until I get what I want" → One draw per decision point; accept the reading

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill's trigger conditions are intentionally broad, including common phrases like 'whatever you think,' 'surprise me,' and even generic ambiguity. This can cause the tarot-based decision process to activate in ordinary conversations where deterministic, task-relevant reasoning would be more appropriate, creating a risk of unreliable or inappropriate guidance. The surrounding skill text partially mitigates this by excluding safety-critical decisions, but accidental invocation remains plausible.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · cards/wands.md (reported line 194)May include surrounding context.

md
Overextension, lack of teamwork, and scattered effort.

## In Technical Context
Expand scope carefully. Early success invites overreach.

---