Security audit

Resume Screener Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language recruiting assistant that analyzes resumes and interview inputs, with no code execution, persistence, credential use, or hidden data movement found.

Before installing, treat this as a tool for sensitive hiring workflows: provide only candidate data you are authorized to process, redact unnecessary personal details, avoid using protected characteristics in decisions, and review any hiring recommendation with applicable HR, privacy, and employment-law obligations in mind.

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
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 (3)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill explicitly processes resumes and interview evaluations, which commonly contain sensitive personal data such as names, contact details, employment history, and potentially protected characteristics, but it does not warn users about privacy handling or data minimization. In a hiring context this is more dangerous because employment decisions are sensitive, regulated in many jurisdictions, and can expose both privacy and discrimination risks if personal data is handled without clear safeguards.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger phrases are very broad, generic requests such as screening resumes or running a hiring process, which increases the chance of accidental or overbroad invocation in contexts where the user did not intend to activate this skill. Because the skill handles hiring workflows and candidate data, unintended activation can lead to unnecessary processing of sensitive information and inappropriate hiring guidance being injected into casual conversations.

Natural-Language Policy Violations

Low

Confidence: 82% confidence
Finding: The description, workflow, examples, and output formats are entirely in Chinese, and the skill does not indicate that language selection is optional or region-specific. Under the policy, forcing a specific language without user opt-in can be a locale-policy issue unless clearly justified.

Static analysis

No suspicious patterns detected.