ClawHub
Back to skill

Security audit

my skill

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward resume review skill that asks for user-provided resume material and gives scoring and rewrite guidance, with no hidden execution, persistence, or external data flow found.

Before installing, treat this as a resume-analysis helper: only provide resumes or job descriptions you intend the agent to read, and consider removing unnecessary personal identifiers such as phone numbers, addresses, IDs, or private employer details. The inspected artifact does not show hidden commands, network retrieval, persistence, or credential access.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list includes broad, conversational phrases such as '帮我看看简历' and '简历能过HR吗', which can cause the skill to activate during ordinary discussion rather than clear user intent to invoke resume processing. In this context, unintended activation is more dangerous because the skill solicits and processes sensitive resume data, increasing the chance of accidental collection or disclosure of personal information.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description, workflow, and required output formats are entirely specified in Chinese, including a strict output template and tone requirements, with no indication that users may choose another language. This is a natural-language policy concern because it imposes a locale/language preference without explicit user opt-in or documented justification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill explicitly asks users to upload resumes in PDF/DOCX/image/text formats and optionally provide a JD, but it gives no warning that resumes commonly contain highly sensitive personal data such as names, phone numbers, emails, work history, and education records. Without a privacy notice or minimization guidance, users may overshare sensitive information and the system may handle it without informed consent or adequate safeguards.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.