Back to skill

Security audit

绩效评估

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only Chinese performance review aid with no executable code or hidden access, but users should avoid pasting unnecessary confidential HR or personal data.

Before installing or using this skill, treat employee performance material as sensitive: share only the minimum needed, redact personal or compensation details when possible, and follow your organization's HR and privacy policies. The artifact itself does not execute code or access data unless the user provides it in the conversation.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill metadata and content define a very broad business-performance capability without clear activation boundaries, permitted inputs, or task-scoping constraints. In an enterprise setting, overly broad activation can cause the skill to be invoked in unintended contexts and process sensitive HR or business data without sufficient guardrails.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly asks users to paste business background, data, and documents, but it does not warn against including sensitive employee performance information, PII, compensation data, or confidential HR records. Because performance reviews commonly contain highly sensitive personal and employment data, this omission increases the likelihood of inappropriate disclosure, overcollection, or mishandling of regulated data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill name includes a China/Chinese suffix and the entire user-facing description is written only in Chinese, with no indication that language selection is optional or region-specific. This may violate a language/locale policy if users are implicitly constrained to one language without opt-in or documented justification.

Content

No source excerpt is available for this finding.