Back to skill

Security audit

Message in a Bottle

Security checks for vulnerabilities and agentic risk

Overview

This skill only returns a random prewritten inspirational “message in a bottle” and does not show sensitive access or hidden behavior.

This appears safe to install for lightweight inspirational messages. Users should only expect prewritten local messages, and should be aware that broad trigger wording may make it activate for some generic requests about random messages or inspiration.

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

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger description includes broad phrases such as 'random message' and 'needs inspiration/wisdom', which can match ordinary user requests and cause the skill to activate when the user did not specifically ask for this tool. Unintended invocation can lead to irrelevant responses, reduced user control, and incorrect tool selection, though it does not directly create code execution or data exfiltration risk in this skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The manifest lists trigger words in Chinese and English, but it does not state whether language selection is based on user preference or context. This can create a mild language/locale policy concern because the skill behavior is tied to specific languages without documenting opt-in or intended locale boundaries.

Content

No source excerpt is available for this finding.