ClawHub
Back to skill

Security audit

Q12敬业度调研助手

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only HR survey helper with no privileged code, but users should avoid sharing identifiable employee survey data with any AI service.

Install only if you intend to use it for employee engagement survey support. Treat survey results as confidential: use aggregated scores, avoid names and free-text comments, avoid very small team breakdowns, and check the AI platform's data retention settings before pasting business or HR data.

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
  • 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 (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The README encourages users to paste survey results for interpretation, which can include sensitive employee sentiment, engagement scores, or small-team data that may enable inference about individuals. Although the document claims local/privacy-preserving usage, it does not warn users to minimize, anonymize, or aggregate personnel data before sharing it with an AI assistant, creating privacy and confidentiality risk in real deployments.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The documented triggers include generic phrases such as "I want to do an engagement survey," "I got the data," and "How to improve team engagement," which could easily appear in normal conversation outside a deliberate skill invocation. The README provides example triggers but does not define constraints, exclusions, or negative examples that clarify when the skill should or should not activate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The workflow trigger phrases include very broad, natural-language inputs such as “我拿到数据了” and “讲讲盖洛普”, which are likely to appear in ordinary conversation outside an explicit intent to invoke this skill. That creates accidental activation risk, causing the assistant to switch into the Q12 survey workflow unexpectedly and potentially produce irrelevant or overconfident HR guidance in unrelated contexts.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description contains many broad HR- and workplace-related trigger phrases such as '员工满意度调查', '团队氛围调研', '留人问题', and '员工离职', which can cause the skill to activate in conversations beyond the intended narrow Q12-survey use case. Over-broad routing increases the chance that users are funneled into this skill in contexts involving sensitive employee relations, privacy, or managerial authority where the skill's advice may be inappropriate or unauthorized.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

This HTML file contains a natural-language comment and behavior that explicitly default the experience to Chinese on every fresh page load, ignoring saved preference and browser locale. That creates a locale policy concern because the skill imposes a specific language without offering user-choice by default.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.