Back to skill

Security audit

Harry Tan(Tin Hou Tam)

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Markdown-only skill with no system access, but its core purpose is to help rewrite academic text to lower PaperPass plagiarism similarity scores.

Install only if you intend to use it for legitimate revision of your own writing. It should not be used to disguise copied work; users should preserve citations, quote or attribute source-derived material, and use rewriting as part of original synthesis rather than as a way to bypass plagiarism checks.

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
  • 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 (2)

Ssd 4

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill gives a structured workflow for rewriting high-similarity passages specifically to reduce plagiarism-detection scores while preserving the original meaning, including thresholds, prioritization, and transformation tactics. In context, this is more dangerous because the entire skill is marketed for lowering PaperPass similarity rates, which facilitates academic misconduct and evasion of integrity controls rather than legitimate citation, summarization, or editorial assistance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest metadata fixes the language to '中文学术论文', and the document consistently defines the skill for Chinese academic writing without indicating that users may choose another language. This is a natural-language locale constraint that can violate policy when it is forced rather than presented as an option or clearly justified as a region-specific compliance requirement.

Content

No source excerpt is available for this finding.