Back to skill

Security audit

周报速整助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward weekly-report formatting assistant and does not ask for system access, external tools, credentials, or persistence.

Installers should expect this skill to reformat work notes into a professional report. Review outputs for accuracy, especially any quantified wording, and invoke it intentionally when you want report formatting rather than casual discussion about reports.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description lists trigger words such as "周报", "工作总结", and "工作汇报" without any constraints, negative examples, or invocation boundaries. These terms are common in everyday workplace conversation, so the skill could be invoked in situations where the user is merely discussing reports rather than requesting transformation into a structured weekly report.

Content

No source excerpt is available for this finding.