ClawHub
Back to skill

Security audit

51mee Resume Profile

Security checks for vulnerabilities and agentic risk

Overview

This skill reads user-provided resumes and uses an AI model to generate candidate profile summaries, with no evidence of hidden execution, persistence, or unrelated data access.

Install only if users are comfortable having uploaded resume contents processed by the AI model. Because resumes often contain personal contact, employment, education, and salary-related information, get the candidate's permission where appropriate and avoid uploading unnecessary sensitive details.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly reads uploaded resume files, extracts their text, and sends the full contents to a large model, but it does not provide any explicit warning, consent mechanism, or data-handling notice. Resumes commonly contain highly sensitive personal data such as names, phone numbers, email addresses, employment history, education, and sometimes government identifiers, so silent transmission to an LLM creates a meaningful privacy and compliance risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The entire skill description, prompt, schema comments, examples, and output template are written to operate in Chinese, but the file does not state that the skill is intentionally limited to Chinese-language users or provide any opt-in choice. This can violate language/locale policy when users have not been offered a language preference.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.