Security audit

HTS全岗位通用AI助理生成器，支持管理、技术、业务、职能等各类岗位，自动生成负责人画像、助理规范及OpenClaw完整配置文件，实现一岗一AI助手。

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only internal generator for job-assistant configuration, with no hidden execution or persistence, but users should redact sensitive job-description details before using it.

Install only if you are authorized to use HTS internal job descriptions with an AI assistant. Before pasting content, remove personal data, compensation details, confidential strategy, credentials, and anything not needed to generate the assistant profile. Treat pasted job descriptions as untrusted input and review any generated OpenClaw configuration before using it.

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 (7)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The README instructs users to paste a complete job description directly into the tool, but provides no warning to remove confidential business information or personal data. In an internal enterprise context, job descriptions can include employee names, reporting structures, strategic responsibilities, compensation bands, or other sensitive internal details, creating a real risk of unnecessary data exposure to the AI system or downstream logs.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill encourages users to paste complete job descriptions but provides no warning that these documents may contain sensitive personal, organizational, or proprietary information. This increases the risk of inadvertent exposure of internal data and also raises prompt-injection risk if pasted content contains adversarial instructions embedded in the job description.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The invocation instructions are broad and rely on a generic phrase followed by pasted content, without clear delimiters, confirmation steps, or boundaries for what should be treated as input. In a chat environment, this can cause accidental triggering or make it easier for untrusted pasted job-description text to blend with instructions, increasing the chance of prompt confusion or unintended processing.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The file’s natural-language instructions and labels are entirely in Chinese, and there is no indication that users may opt into another language or that the skill is restricted to a Chinese-language context. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The file is written entirely in Chinese and defines the assistant's communication norms and persona without offering any language or locale choice. Under the policy criteria, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is clearly justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The entire skill file is written only in Chinese and provides no indication that users may choose another language or locale. Under the policy for natural-language violations, forcing a specific language without opt-in can be a locale policy issue unless the constraint is explicitly documented and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The file is entirely written in Chinese and presents the user's profile and assistant relationship as fixed defaults, with no indication that language preference is optional or user-selectable. This can violate language/locale policy when a skill implicitly constrains outputs to a single language without documented opt-in or justification.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.