Back to skill

Security audit

mfg-exp-distill

Security checks for vulnerabilities and agentic risk

Overview

This is a manufacturing best-practices reference skill with no code execution or hidden access, with only minor scope and language caveats.

Before installing, expect this skill to be most useful for Chinese-language manufacturing operations and improvement-methodology questions. Review whether you want auto-updated manufacturing reference content from the listed business/industry sources, and be aware it may activate broadly on manufacturing topics.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The invocation description says to use the skill whenever 'the user works in manufacturing,' 'wants to learn manufacturing experience,' or 'wants to distill manufacturing methodologies.' These conditions are broad and lack clear trigger phrases, exclusions, or boundaries for when the skill should not activate, which could cause unintended invocation across many general manufacturing discussions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill metadata and the entire user-facing description are written only in Chinese, with no indication that language is selectable or that Chinese is an intentional regional constraint. This can violate language/locale policy when the skill implicitly enforces a single language without user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.