Back to skill

Security audit

Supplier Quality Agreement

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Chinese-language supplier quality agreement drafting and review guide with expected local document output and no evidence of hidden, destructive, or exfiltrating behavior.

Before installing, note that this skill is designed primarily for Chinese supplier quality agreement work and may create local report files. Use it with appropriate handling for confidential supplier, customer, contract, or legal-review material, and treat generated clauses as drafts for qualified legal review.

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 (2)

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
L136 explicitly states `中文文档`, and the entire skill description/output naming is Chinese-centric without indicating user choice or opt-in for language. Under the policy, forcing a specific language is a natural-language policy violation unless the skill offers language selection or clearly documents a justified locale-specific constraint.

Missing User Warnings

Low
Confidence
91% confidence
Finding
The skill explicitly instructs the agent to write Markdown and TXT files to local storage, but it does not clearly warn the user that files will be created or where they will be written. This can lead to unintended local side effects, confusion about data persistence, and accidental storage of potentially sensitive contract or supplier information on disk.

Static analysis

No suspicious patterns detected.