Back to skill

Security audit

Management Review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language ISO 9001 management-review assistant that creates local review documents, with no evidence of hidden execution, credential use, network access, or persistence beyond disclosed output files.

Before installing, treat generated management-review files as potentially sensitive business records. Use the skill in a deliberate working folder, review generated documents before sharing, and do not provide confidential audit or performance data unless you are comfortable storing it in local output files.

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
87% confidence
Finding

The description is written as a fixed Chinese-language operating mode and does not mention any option to use another language. This can violate language/locale policy expectations when a skill forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly states it will write multiple txt/md files into the user's working directory, but it provides no requirement to ask for confirmation, preview outputs, or let the user choose paths before writing. Unprompted file creation can overwrite existing documents, leak sensitive management-review content into unintended locations, or be abused to persist data on disk when the user expected a conversational-only interaction.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.