Security audit

古人诗词大师

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent classical Chinese poetry assistant with purpose-matched local data and helper scripts, not evidence of malicious behavior.

Install if you want a Chinese classical poetry assistant. Be aware it may activate on broad poetry terms, and graph output creates an HTML file that loads D3 from d3js.org when viewed.

SkillSpector

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

Confidence: 86% confidence
Finding: The trigger list contains broad terms like '诗人', '古诗', '写诗', and '知识图谱', which can cause the skill to activate in loosely related conversations. Overbroad activation increases the chance that file access, script execution, or HTML generation pathways are invoked unexpectedly in contexts where the user did not intend to use this skill.

Vague Triggers

Medium

Confidence: 81% confidence
Finding: The invocation guidance groups broad 'analysis' and 'query' requests without clear limits, making routing ambiguous. In a skill that can read files, run local scripts, and produce HTML, ambiguous activation boundaries can lead to unintended capability use or make prompt-injection through user-supplied poem text harder to contain.

Static analysis

No suspicious patterns detected.