Back to skill

Security audit

Auto Dream Light

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent local memory-consolidation workflow that discloses its file updates and does not include hidden code, network access, or unrelated behavior.

Install this only if you want the agent to read and update your local memory notes. Use clear commands when invoking it, and review memory-file diffs and any commit it creates after a run.

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
  • 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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The listed trigger phrases include multiple Chinese-only activations alongside one English phrase, but the document does not state that language choice is optional or that the skill supports equivalent triggers in the user's preferred language. This can be a natural-language policy issue because it biases activation toward a specific language without explicit opt-in or justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger phrase dream now is short, generic, and easy to invoke accidentally in normal conversation or as quoted text. In a skill that can perform repository writes and optional commits, ambiguous invocation increases the chance of unintended state-changing actions without sufficiently explicit user consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The workflow explicitly includes writing target files, updating a dream-log, and committing changes, but it does not require any user-facing warning or confirmation before modifying repository state. This creates a risk that users invoke the flow without understanding that persistent files and version history may be changed.

Content

No source excerpt is available for this finding.