Back to skill

Security audit

看板需求书台

Security checks for vulnerabilities and agentic risk

Overview

This is a simple dashboard-requirements writing skill with no executable code, persistence, credential access, or data exfiltration behavior.

This skill is reasonable to install for drafting BI or data-dashboard requirement documents. Users should be aware that broad Chinese trigger phrases may activate it during general reporting conversations, but it does not request unusual permissions or perform actions outside the chat.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger keyword "怎么做报表" is broad natural language that can overlap with ordinary user requests outside this specific skill, making unintended activation more likely. The file does not provide exclusion conditions or tighter scope boundaries for when this phrase should or should not invoke the skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

Examples like "按上面的结果改成更简短的版本" and "把这些整理成一张表" are common follow-up phrases that could apply to many unrelated skills. Without explicit context limits stating these only apply after this skill has already produced a dashboard brief, the invocation boundary is ambiguous.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.