Back to skill

Security audit

Thesis Results Writer

Security checks for vulnerabilities and agentic risk

Overview

This is a narrowly scoped writing aid for Chinese thesis results chapters, with no code execution, persistence, credential use, or hidden data handling.

Install this if you want help drafting Chinese thesis results sections. Review generated academic text carefully, provide real data rather than placeholders, and do not rely on the skill to invent statistics, interview quotes, or findings.

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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction says to use this skill only for the results part of a Chinese academic paper and makes Chinese the default output format. This is a natural-language locale constraint that does not present a user choice or opt-in, which can violate language/locale policy requirements.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest text specifies a "Chinese academic results chapter writer" and instructs the model to "write a rigorous Chinese results chapter," which imposes a language choice in natural-language metadata. This is a locale/language policy concern because the file does not indicate that Chinese is optional, user-selected, or limited to a justified region-specific use case.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file contains natural-language instructions that steer output into a specific language/locale context. Because it presents Chinese-only templates and scope without indicating user opt-in or a documented regional requirement, it may violate the policy against forcing a specific language without choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.