Back to skill

Security audit

Research Paper Quality Filter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward academic paper filtering guide that writes disclosed local audit logs and does not include hidden code, credential use, network behavior, or unsafe automation.

Install only if you want paper filtering decisions saved into a persistent local research log. Review the chosen domain value because it determines the output path, and avoid feeding sensitive paper notes or private review data unless you are comfortable storing them in that workspace file.

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)

Missing User Warnings

Low
Confidence
89% confidence
Finding
The skill explicitly states it will create directories and append results to a local log file, but it does not clearly warn the user that running it modifies the local filesystem persistently. This is not inherently malicious, but silent persistent writes can surprise users, overwrite expectations about agent behavior, and create privacy or workspace hygiene issues in research environments.

Static analysis

No suspicious patterns detected.