Back to skill

Security audit

Supplier Development

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese supplier-improvement report generator with disclosed document output and no evidence of hidden access, exfiltration, persistence, or unsafe behavior.

Before installing, confirm you want a Chinese-language supplier-development workflow and only provide supplier performance data you are allowed to place in generated reports. If the agent tries to run scripts/build_report.py, verify the script's source and output directory first because the script was not included in the inspected artifact.

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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The natural-language description explicitly states 中文文档, indicating the skill is intended to produce Chinese documents. Because no user opt-in or alternative language option is offered, this is a locale/language policy concern under the stated rule.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill explicitly instructs the agent to generate Markdown and text files on disk, but it does not require notifying the user, confirming the destination, or constraining the output path. In an agent environment, silent artifact creation can cause unintended data persistence, clutter shared workspaces, or write sensitive business planning content to locations the user did not expect.

Content

No source excerpt is available for this finding.