ClawHub
Back to skill

Security audit

algorithm-solver

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed algorithm-solving helper that runs local tests and performs algorithm-related web searches, with no evidence of hidden persistence, credential access, destructive behavior, or exfiltration.

Before installing, expect this skill to run generated code tests with Bash when possible and to perform web searches for real-world algorithm applications even if you did not separately ask for web research. Avoid giving proprietary or sensitive problem statements if you do not want related algorithm context searched externally.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

该技能声明会在用户提出算法题、数据结构问题、或要求解题时自动触发，匹配范围较宽，容易在泛化的“问题求解”场景被误调用。过宽的自动触发会导致不必要的工具暴露，尤其该技能还具备 Bash 和 WebSearch 权限，增加误用和越权执行风险。

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

该技能的核心定位是算法题解析与求解，但却要求“必须执行”联网搜索工业界应用，这会把任务范围从本地推理扩展到外部信息获取。对用户未明确请求联网时，技能会主动向外发送查询，带来不必要的数据外泄、提示词偏移和供应链信息污染风险。

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

强制使用 WebSearch 调研工业应用与“算法解题教练”的主要目标不直接相关，属于不必要的外部能力升级。这样的设计会增加攻击面：外部搜索结果可能包含误导内容，且会让技能在解题场景中稳定触发网络访问，削弱最小权限原则。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

Line L297 requires all explanations and comments to be in Chinese, creating a fixed language policy regardless of user preference. This is a natural-language policy issue because it forces a locale/language choice without opt-in or an alternative path.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.