Back to skill

Security audit

Academic Writing

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward academic-writing helper with no code execution, persistence, credential access, or hidden data flows.

Before installing, treat this as a writing and citation-formatting helper, not an authority on factual correctness. Verify references yourself, especially because the skill asks the agent to produce academic citations but does not provide its own retrieval or validation mechanism.

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
  • 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill exposes a very broad academic-writing capability without clear activation boundaries, topic restrictions, or refusal conditions. In an agent setting, this increases the chance the skill is invoked for unintended tasks such as generating misleading academic content, unsupported citations, or content outside its intended domain, especially because the instructions are expansive and authoritative.

Content

No source excerpt is available for this finding.