Back to skill

Security audit

AI Academic Mentor

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only academic writing and paper-analysis helper with no hidden execution, persistence, or credential behavior found.

Installers should understand that this skill is meant to read and analyze academic documents or text they provide. Avoid providing confidential papers or unpublished research unless you are comfortable sharing them with the agent environment, but the artifact itself does not request hidden access or unsafe authority.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

Line L003 states that the document provides guidance for English academic writing, which imposes a specific language context. Because the file does not indicate user opt-in or explain a region- or task-specific necessity beyond the language preference itself, this can be interpreted as a locale/language policy issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.