Back to skill

Security audit

Meme Lord

Security checks for vulnerabilities and agentic risk

Overview

This is a small Chinese meme-assistant skill that discloses its web-search behavior and does not include code, persistence, credential access, or hidden installation behavior.

Install this if you want a Chinese meme helper and are comfortable with it using web search for meme origins and trend checks. Avoid sending private or sensitive text for lookup, since searched phrases may be shared with external search providers.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The top-level skill metadata includes broad trigger phrases such as “meme”, “整活”, and “抽象”, which can appear in normal conversation and cause the skill to activate unexpectedly. Unintended activation is risky here because the skill’s documented behavior includes external web searches, potentially causing unnecessary network access and user-surprising behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file describes the skill as a Chinese internet meme skill and presents all activation and operating instructions in Chinese, effectively constraining the interaction to a specific language/locale. It does not explicitly offer language choice or explain that the locale limitation is an intentional, justified constraint for a region-specific tool.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The decoder trigger list contains ambiguous phrases like “什么意思” and “出处是什么”, which are common across many non-meme conversations. This can route unrelated requests into the meme skill, degrading correctness and potentially triggering unnecessary searches.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The meme-making trigger list includes vague activators such as “整活” and “变成梗”, which are colloquial and may be used in broader creative contexts. This creates a prompt-routing weakness where the wrong skill may engage, leading to confusing or unintended outputs.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly mandates online searches and hot-list fetching for several functions, but it does not require user notice or consent at the moment of external access. This can expose user-provided meme text or interests to third-party services unexpectedly and violates least-surprise/privacy expectations.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The trigger phrase "热梗" is short and context-light, so it may match incidental mentions rather than a deliberate request to run the trending-meme workflow. The description does not specify required phrasing, invocation context, or non-trigger examples.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.