Back to skill

Security audit

撒大大撒

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language simulated weather lookup skill with no executable package, credentials, persistence, or hidden high-impact behavior.

Before installing, note that this skill returns hardcoded simulated weather data, not live forecasts, and its broad Chinese weather triggers may activate on ordinary weather questions.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 1)May include surrounding context.

md
---
# 发布必备的元数据(YAML frontmatter)
name: simple-weather
slug: simple-weather  # 唯一标识,小写+横杠,发布时用

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation phrases are broad everyday weather terms like '天气', '下雨', and '今天天气怎么样', which can cause the skill to trigger on many ordinary conversations rather than only clear requests to use this specific capability. Overly broad activation increases the chance of unintended invocation, routing errors, and context leakage into the skill when the user did not explicitly intend to invoke it.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill instructions, trigger phrases, and usage description are entirely in Chinese, but the file does not state that the skill is intentionally limited to Chinese-speaking users or offer any language/locale opt-in. Under the stated policy, forcing a specific language without user choice or documented justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.