Security audit

Jd Translator

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed JD analysis and interview-prep helper with no evidence of credential access, persistence, exfiltration, or destructive behavior.

Before installing, be aware that the skill is primarily written for Chinese-language JD workflows and may use public company research to improve analysis. Do not include private employer information unless you are comfortable sharing it with the active agent/model, and look for clearer consent/retention terms if future feedback collection is added.

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
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (8)

Intent-Code Divergence

Medium

Confidence: 92% confidence
Finding: The self-assessment claims the skill performs only read-only text analysis and has no sensitive operations, yet the same document states the skill includes scripts and plans to collect and record user interview outcomes. This creates a misleading security posture that can cause reviewers or operators to under-scope permissions, data handling, and execution risk, especially if helper scripts are later run or user feedback contains personal data.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The skill description includes trigger phrasing like '当用户说"帮我分析这个岗位"时', which is broad everyday language and can cause the skill to activate in normal conversation even when the user did not intend to invoke this specific skill. Over-broad activation increases the chance of incorrect routing, unnecessary context capture, and user intent hijacking in multi-skill environments.

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: The metadata and content strongly assume Chinese output and usage without indicating user choice, which can override the user's preferred language. This is risky because it can degrade usability, mis-handle multilingual sessions, and cause the assistant to ignore explicit user language preferences.

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: This markdown file contains user-facing instructional content exclusively in Chinese, and there is no indication that users may request another language or that the material is intentionally scoped to a Chinese-only audience. Per the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: This markdown file’s natural-language instructions and examples are entirely in Chinese, and there is no indication that users can choose another language or that the skill is intentionally limited to a Chinese-language audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The entire skill document is written in Chinese and does not indicate that the language is configurable or limited to a justified region-specific audience. Under the policy rule for natural-language violations, this can be considered a forced locale/language choice without user opt-in.

Intent-Code Divergence

Low

Confidence: 84% confidence
Finding: Saying there is no internal persistent state conflicts with the later plan to record actual usage feedback and interview results. Even if this is roadmap functionality rather than current behavior, the inconsistency can lead to inadequate retention, consent, and access-control decisions once feedback collection is implemented.

Natural-Language Policy Violations

Low

Confidence: 92% confidence
Finding: This code file contains natural-language instructions and user-facing output exclusively in Chinese, including the module docstring and usage guidance. Under the policy rule for language/locale constraints, forcing a specific language without user choice is a policy concern because non-Chinese-speaking users are not given an alternative.

Static analysis

No suspicious patterns detected.