Back to skill

Security audit

北京花粉监测

Security checks for vulnerabilities and agentic risk

Overview

This skill is a purpose-aligned Beijing pollen data wrapper that queries public APIs and does not show hidden persistence, credential use, or destructive behavior.

Install only if you are comfortable with a Chinese-language Beijing pollen tool that makes outbound requests to the configured public pollen API host and requires bash, curl, and jq. It does not appear to access private files or credentials.

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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill invokes a shell script and explicitly requires shell-capable binaries (curl, jq), but it does not declare any tool scope such as permissions or allowed-tools. That means an agent may execute shell-capable actions without an explicit least-privilege boundary, increasing the chance of unintended command execution or misuse if arguments are later influenced by user input or if the script changes.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The display name, short description, and default prompt all require Chinese comprehension, and the file does not indicate that users can opt into another language or that the skill is intentionally restricted to a Chinese-speaking or Beijing-only audience for policy reasons. Under the language/locale policy rule, forcing a specific language without user opt-in is a reportable natural-language policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This shell script presents usage text and generated report content entirely in Chinese, and later hard-codes Chinese date/time formatting and Chinese report strings. That creates a natural-language locale policy issue because the skill does not offer the user a language choice or clearly document a justified China-only locale restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

该 markdown 文件以中文编写并面向命令使用说明,但没有说明这是仅面向中文用户的区域性技能,也没有提供语言/locale 选择。按规则,强制特定语言而无用户选择或明确合理化说明,属于自然语言政策风险。

Content

No source excerpt is available for this finding.