Back to skill

Security audit

My Skill

Security checks for vulnerabilities and agentic risk

Overview

The skill is a small Markdown-only test/chat instruction with no executable code or persistence, but its weather description conflicts with its Feishu chat instructions.

Before installing, confirm whether this is meant to be a weather skill or a Feishu chat-test skill. The current artifact appears low risk, but the publisher should fix the mismatched description and clearly label the intended language and platform.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The top description says the skill fetches current weather information via a weather API, but the later documentation describes a simple Feishu chat skill that receives user messages and replies in groups or direct messages. These are materially different stated intents, so the file's own documentation actively conflicts about what the skill is supposed to do.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The natural-language content in the skill body requires users to understand Chinese, but the file does not indicate that this is a region-specific skill or provide any language selection. This can violate language/locale policy expectations when users are not given an explicit choice.

Content

No source excerpt is available for this finding.