Back to skill

Security audit

knowledge-miner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed teaching aid that reads Git history or visible conversation evidence to explain knowledge, with no executable payload or hidden data flow found.

Install this if you want a Chinese-language learning assistant for Git commits or visible-session summaries. Be aware that phrases like '刚才' or '上文' can direct it to summarize the current conversation, so ask for a specific commit hash or clarify the source when you want a narrower review.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill treats broad phrases such as '刚才'、'上文'、'当前对话' as triggers for session-analysis mode. That can cause unintended activation on ambiguous user requests, making the skill analyze visible conversation context when the user may have meant repository history or a narrower target, which increases the chance of over-collection and accidental disclosure of contextual data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

L149 要求“首次出现的英文术语同时给出简短中文解释”,整体文件也持续以中文规定输出结构和教学方式,但没有说明这是可选项或需用户同意。此类固定语言/locale 约束属于自然语言策略限制,可能违反应允许用户语言选择的组织政策。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file presents all guidance exclusively in Chinese, and nowhere indicates that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The title and the file’s instructional content are entirely in Chinese and function as guidance for how the skill should respond. This effectively imposes a specific language/locale without stating that the user can choose another language or opt in to Chinese, which matches the language-policy violation criteria.

Content

No source excerpt is available for this finding.