Back to skill

Security audit

Dream interpretation

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only Freudian dream interpretation skill with no code execution, persistence, or data access, though it may invite sensitive personal disclosures.

Install only if you are comfortable using a Freudian, non-clinical dream interpretation style. Avoid sharing details you would not want processed in chat, especially trauma, sexual history, childhood experiences, or acute mental-health concerns; seek professional or crisis support for distressing or safety-related situations.

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
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 216)May include surrounding context.

md
7. Leave room for tension: the moral complexity of the wish is exposed to the light, but **no moral judgment is made**

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This skill solicits and processes highly sensitive mental-health, childhood, sexual, and intimate personal content, but the user-facing description does not clearly warn users before they engage. In this context, missing an upfront sensitivity/disclaimer notice increases the risk of oversharing, uninformed consent, and inappropriate use in situations involving distress or psychological crisis.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The manifest description lists trigger words primarily in English and then adds the Chinese phrase '梦境解读', indicating multilingual activation behavior. Because the skill does not explain language selection, user opt-in, or any locale policy, this creates a language/locale policy concern under the natural-language policy rule.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% 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 · SKILL.md (reported line 263)May include surrounding context.

md
- Pure wish-fulfillment theory vs. traumatic repetition dreams — this is the most famous "fault line" within Freud's theoretical system
- The late Freud acknowledged: certain recurring nightmares may be products of **compulsion to repeat (Wiederholungszwang)** rather than wish fulfillment
- This self-correction is recorded in *Beyond the Pleasure Principle* (1920)
- **How to handle**: When encountering a typical traumatic repetition dream, do not forcibly apply the wish-fulfillment framework; instead, state truthfully — "According to the late Freud's view, this dream may go beyond the scope of pure wish fulfillment"

### Confidence Notes

Static analysis

No suspicious patterns detected.