ClawHub
Back to skill

Security audit

Food History Prose

Security checks for vulnerabilities and agentic risk

Overview

This is a low-risk, instruction-only writing skill for Chinese food-history prose, with no code, credentials, installs, or data access.

Install only if you want a Chinese-language writing guide for food-history essays. For broader audiences, the publisher should add a clear language policy or bilingual guidance, and users should verify any historical citations the model generates.

SkillSpector

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
Confidence
91% confidence
Finding
The skill is entirely written as mandatory Chinese-only guidance and does not provide a user language choice, fallback behavior, or a documented reason for restricting usage to Chinese. In a general-purpose agent environment, this can exclude users, cause the agent to ignore user language preferences, and lead to reliability and accessibility failures when the invoking user does not read Chinese.

Static analysis

No suspicious patterns detected.