Back to skill

Security audit

求职信息搜索

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward job-search helper that searches public recruiting and interview resources without requesting local access, credentials, persistence, or system changes.

Before installing, be aware that the skill may search the web for job, salary, company, and interview information. Avoid providing unnecessary personal identifiers, private application materials, or account credentials; verify postings and salaries from multiple sources before acting on them.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

All natural-language description and operating instructions are written as if the skill is intended to operate only in Chinese, with no indication that users may choose another language. Under the policy, forcing a specific language without user opt-in is a locale/language policy concern unless the restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrases are very broad generic intents such as '找工作' and '查薪资', which can overlap with many normal user requests and cause the skill to activate outside a narrowly scoped context. Over-broad activation can route unrelated queries into web-search-driven behavior, increasing the chance of unintended browsing, irrelevant data collection, or bypass of more appropriate system behaviors.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.