Back to skill

Security audit

Norman Mailer Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language writing and analysis persona skill with no code, data access, persistence, or hidden execution behavior.

Installers should expect this skill to shape answers around Norman Mailer-style literary, cultural, and political analysis, likely in Chinese unless the user asks otherwise. It does not appear to access private data or run commands.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown skill is written entirely in Chinese and presents all headings, instructions, and examples in that language, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-only audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.