Back to skill

Security audit

Supplier Management Plan

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a document-generation helper, but it tells the agent to run a relative local script that is not included in the package and to create files in the workspace.

Review before installing. The document-generation behavior is understandable, but the package should either include the referenced builder script or remove the command instruction; otherwise an agent may fail or resolve `scripts/build_report.py` from an unintended workspace location. Users should also confirm where `./out` points and whether same-day report files may be overwritten.

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 includes '中文文档', which indicates the skill is intended to produce Chinese-language documents. Because the file does not offer users a language/locale choice or explain a necessary region-specific restriction, this is a language-policy violation under the stated rules.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly instructs the agent to invoke scripts/build_report.py and write .md and .txt files into ./out, but it does not warn the user that local files will be created or potentially overwritten. This can lead to unintended filesystem side effects, especially in shared workspaces or automation contexts where users may not realize the skill performs persistent writes.

Content

No source excerpt is available for this finding.