Back to skill

Security audit

Chengyu Card Poster

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Chinese idiom social-post generator that creates a local markdown draft, with no evidence of credential access, networking, hidden execution, or destructive behavior.

Installers should expect the skill to generate Chinese social-post copy and save a markdown draft locally. Consider narrowing the trigger and confirming the filename before saving if accidental invocation or workspace clutter matters.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes a very broad phrase, "chengyu", which can overlap with ordinary multilingual conversation and unintentionally activate the skill outside the user's clear intent. This can cause unexpected execution of the skill workflow and, in this case, chain into automatic content generation and file-writing behavior without sufficiently explicit invocation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs the agent to write generated content directly to output/xhs-{成语名}.md without any prior user-facing disclosure or confirmation. Unannounced file creation is risky because it can surprise users, clutter workspaces, and combine with accidental triggering to perform state-changing actions the user did not clearly authorize.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.