Back to skill

Security audit

backend admin develop skill

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for a Vue/Flask admin portal; it describes powerful admin and S3 features but does not include hidden execution, persistence, or deceptive behavior.

Install only if you want Chinese-language guidance for this Project Portal admin system. Treat RBAC changes, password resets, account disabling, S3 deletion, uploads, and file proxying as administrator-only actions that can affect access, expose files, or lose data if used carelessly.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (6)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
93% confidence
Finding

The S3 service section includes bucket creation, deletion, renaming, and directory deletion, which are potentially destructive and irreversible operations. The markdown does not provide any warning about possible data loss or the need for backup/confirmation before performing these actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The markdown describes role creation, editing, deletion, and permission assignment in an admin system, but it does not include any warning that these actions can change access control or disrupt user access. Because this is a markdown skill description covering safety-relevant administrative changes, it should disclose the potential impact on permissions and system access.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file advertises password resets and enable/disable user operations without any warning that these actions affect account access and may lock users out. In markdown, user-impacting identity and access operations should be accompanied by an explicit notice about their consequences.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The markdown states that images can be uploaded and sent to S3-backed APIs, but it does not warn users that files may leave the local environment and be stored in external or separate storage services. This is a privacy- and data-handling-relevant behavior that should be disclosed in the skill description.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill file presents its operational documentation entirely in Chinese, and there is no indication that the language is optional, user-selectable, or required for a region-specific purpose. This can violate a language/locale policy when a skill effectively forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The file describes a proxy endpoint that directly accesses files in S3 storage, but it does not warn that this may expose stored content through proxied retrieval. For a markdown skill description, direct file-access behavior should be disclosed so users understand the privacy and data exposure implications.

Content

No source excerpt is available for this finding.