Security audit

ym-lyric-rhyme-workshop

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only Chinese lyric-writing helper with disclosed limits and no evidence of hidden access, persistence, networking, or destructive behavior.

Install this if you want a Chinese-oriented lyric and rhyme assistant. Expect outputs to default to Chinese pop/folk/rap/guofeng structures and Chinese rhyme conventions; if you need multilingual lyric writing, this skill may be too narrow without adaptation.

A.I.G

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

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 (5)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger list includes very generic phrases such as "lyrics" and broad lyric-writing requests, which can cause the skill to activate during ordinary multilingual conversation rather than only when a user explicitly wants this workflow. This is not a direct security exploit, but it can lead to unintended routing, context capture, or interference with higher-priority skills.

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The documented trigger set lacks clear activation boundaries and includes ambiguous phrases that may match common user utterances beyond the intended lyric-writing use case. In an agent ecosystem, this increases the risk of accidental invocation, misrouting user requests, and exposing user inputs to a skill that was not actually needed.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: This markdown file is entirely framed in Chinese and defines lyric-writing defaults such as Chinese character counts per line, rhyming conventions, and genre rules as the default structure. There is no indication that the user can choose another language or locale, which can constitute a language/locale policy violation under the rule for natural-language policy concerns.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The template is entirely specified in Chinese and requires Chinese-specific constraints such as counting Han characters and using the '十三辙' rhyme system. This effectively mandates a single language/locale for output, with no indication that users may choose another language or locale.

Natural-Language Policy Violations

Low

Confidence: 92% confidence
Finding: The title and entire content are presented only in Chinese, and there is no indication that the skill is intentionally region- or language-specific or that users can opt into another language. Under the policy, forcing a specific language without user choice can be a natural-language policy violation.

Static analysis

No suspicious patterns detected.