Back to skill

Security audit

51mee Background Check List

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward background-check checklist skill, but it handles sensitive candidate information that users should provide only with authorization and minimization.

Before using this skill, make sure the candidate has authorized the background check and provide only the information needed to generate the checklist. Redact unnecessary identifiers and avoid submitting government IDs, financial details, health information, family details, or unrelated personal data.

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

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This skill processes highly sensitive candidate personal data, yet it does not prominently instruct users to submit only authorized, minimum-necessary information before use. Even though it claims local inference and no third-party sharing, users may still provide excessive or unauthorized PII, creating privacy, legal, and compliance risk under hiring and personal-data regulations.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The activation text says the skill is for when a user is preparing to hire a candidate and wants a background-check checklist and question template, but it does not define precise trigger phrases, boundaries, or cases where the skill should not activate. In a markdown skill description, this can lead to unintended invocation for adjacent recruitment or resume-review requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.