Security audit

Interview Mock Partner

Security checks for vulnerabilities and agentic risk

Overview

This skill appears benign: it generates mock medical interview content locally, with no network, credential, persistence, or hidden behavior found.

This is reasonable to install from a security perspective. If a future version implements the documented --output option, choose an intended workspace path and avoid naming an existing important file unless you mean to replace it.

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

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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 (1)

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: This markdown file documents an --output parameter for writing results to a file, but it does not explicitly warn users that the skill may create or overwrite files. Although later risk tables mention file system access, there is no direct user warning near the parameter or usage description about the practical impact on user data.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.