Back to skill

Security audit

Dk Helloworld 001

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to only echo supplied text, but its instructions contain unrelated registry API documentation that should be cleaned up.

This is acceptable to install as a simple test skill, but treat anything you pass to it as visible output. The publisher should remove the unrelated registry API table or clearly separate it into a different skill to avoid confusion.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The natural-language instructions and descriptions in this skill file are presented only in Chinese, with no indication that the user can choose another language or that the skill is intentionally region-specific. Under the stated policy, forcing a specific language without user opt-in is a locale-policy concern.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Authentication, search, publishing, deletion, and download endpoints are unjustified for a purported console-printing utility. Even if only documented, these capabilities indicate possible scope expansion, hidden backend integration, or deceptive packaging that could lead users to trust and install a skill with much greater operational reach than expected.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill presents itself as a simple hello-world printer, but the documentation also includes a broad registry/authentication/search/publish API surface unrelated to that claimed purpose. This mismatch is dangerous because it can conceal undeclared remote capabilities or confuse reviewers into approving a skill whose actual scope is much larger than advertised.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This markdown file describes accepting any string input and printing it directly to the console, but it does not warn users that provided text may be exposed in terminal logs, shared sessions, or recorded outputs. For a markdown skill description, direct disclosure of user-provided content is a behavior that can affect privacy and should be called out.

Content

No source excerpt is available for this finding.