Back to skill

Security audit

Lobster Buddy

Security checks for vulnerabilities and agentic risk

Overview

This is a simple electronic pet skill with limited, disclosed local memory use and no code execution or external access.

Installers should be comfortable with the skill keeping a small persistent pet profile tied to their user ID and occasionally adding pet-style comments to replies. The trigger wording could be tightened, but no malicious, destructive, credential-related, or external data-transfer behavior was found.

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 (2)

Vague Triggers

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The front-matter description says the skill triggers when the user asks "我的宠物", "看看我的buddy", or "抽宠物", but later interaction examples use different phrases such as "看看 buddy" and "宠物属性". This inconsistency leaves the exact activation scope unclear and may cause unintended or missed invocations.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

Phrases like "我的宠物" and "看看 buddy" are short natural-language expressions without any stated contextual limits, and the file does not provide negative examples or exclusion conditions. In a conversational setting, this can overlap with ordinary chat and make activation boundaries unclear.

Content

No source excerpt is available for this finding.