ClawHub
Back to skill

Security audit

Dream Analyzer - AI解梦与潜意识分析

Security checks for vulnerabilities and agentic risk

Overview

This is a simple dream-interpretation prompt skill with no code execution, data access, persistence, or hidden system changes, though its tone is psychologically blunt.

Install only if you want blunt, symbolic dream interpretation. Do not treat its outputs as diagnosis, therapy, or reliable personality assessment, and avoid using it for crisis, trauma, self-harm, or serious mental-health concerns.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill presents psychological-style interpretation and explicitly instructs the model to avoid reassurance and deliver 'the truth,' but it provides no warning that outputs are speculative, non-clinical, and may be emotionally harsh. In the context of dream analysis and personality inference, this can mislead vulnerable users, intensify distress, and blur the boundary between entertainment and mental health guidance.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation trigger is broad enough to fire on general mentions of dreams, nightmares, subconscious topics, or any request for interpretation, which can cause the skill to engage in contexts the user did not clearly opt into. In this skill, that is more dangerous because the output is designed to be harsh and psychologically interpretive, increasing the risk of unsolicited mental-health-style analysis or distressing responses.

Content

No source excerpt is available for this finding.