ClawHub
Back to skill

Security audit

简历评估器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese-language resume evaluator that reads user-selected resume files and produces a ranked assessment table, with no hidden execution, persistence, or network behavior found.

Install this only if you want a Chinese-language resume screening workflow. Use a dedicated folder containing only the resumes you intend to evaluate, and review outputs before sharing because they may include personal candidate details such as names, age, education, employer history, and inferred fit scores.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The manifest description and all operational instructions are written to require Chinese-language behavior, including fixed Chinese output labels and evaluation text. There is no opt-in, language selection mechanism, or documented justification that this skill is limited to a Chinese-language or region-specific use case.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs bulk scanning and reading of all resumes in a user-specified directory, but provides no boundary checks, minimization rules, or privacy notice for handling highly sensitive personal data. Because resumes commonly contain PII such as names, contact details, employment history, and education records, this design can lead to over-collection or accidental exposure of unrelated files if the selected directory is broader than intended.

Static analysis

No suspicious patterns detected.