Back to skill

Security audit

Content Research & Sourcing

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable content fact-checking skill whose instructions are coherent, disclosed, and aimed at reducing publication risk.

Before installing, understand that this skill is for research and sourcing discipline, not professional medical, legal, tax, or financial advice. For high-stakes claims, keep its disclaimers and human-review expectations, and use qualified professionals where publication risk warrants it.

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
Category
Not specified by scanner
Confidence
88% confidence
Finding

The framework acknowledges YMYL claims need a heightened sourcing bar, but it does not explicitly warn users that health and financial content can materially affect real-world decisions and should be verified by qualified professionals. In a content-production workflow, that omission can normalize publication of high-stakes guidance that appears well-sourced yet is still interpreted as professional advice.

Content

No source excerpt is available for this finding.