Back to skill

Security audit

Kpop Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill tracks K-Pop updates using public web sources and disclosed local tracking files, with optional scheduled checks only when the user asks.

Before installing, be aware that this skill stores followed artists and reported URLs in local workspace files, uses a browser profile to check social and shopping sites, and can create twice-daily cron checks only if you explicitly request automatic updates.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (15)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The declared purpose emphasizes idol-update tracking, but the skill also performs persistent local configuration and history management. Hidden state changes are risky because users may invoke a content-tracking skill without realizing it will modify local data, creating opportunities for stealthy persistence or undesired data retention.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared purpose emphasizes idol-update tracking, but the skill also performs persistent local configuration and history management. Hidden state changes are risky because users may invoke a content-tracking skill without realizing it will modify local data, creating opportunities for stealthy persistence or undesired data retention.

Content

No source excerpt is available for this finding.

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 79)May include surrounding context.

md
- New song MV or audio on YouTube this week
- Concept photos, tracklist, teaser schedule

Output rules:
- List confirmed comeback date (or "目前無回歸消息")
- If new MV/song released this week → include YouTube link
- If comeback is announced but not yet released → show schedule/timeline

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 95)May include surrounding context.

md
- New song MV or audio on YouTube this week
- Concept photos, tracklist, teaser schedule

Output rules:
- List confirmed comeback date (or "目前無回歸消息")
- If new MV/song released this week → include YouTube link
- If comeback is announced but not yet released → show schedule/timeline

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 124)May include surrounding context.

md
- New song MV or audio on YouTube this week
- Concept photos, tracklist, teaser schedule

Output rules:
- List confirmed comeback date (or "目前無回歸消息")
- If new MV/song released this week → include YouTube link
- If comeback is announced but not yet released → show schedule/timeline

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 136)May include surrounding context.

md
- New song MV or audio on YouTube this week
- Concept photos, tracklist, teaser schedule

Output rules:
- List confirmed comeback date (or "目前無回歸消息")
- If new MV/song released this week → include YouTube link
- If comeback is announced but not yet released → show schedule/timeline

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 155)May include surrounding context.

md
- New song MV or audio on YouTube this week
- Concept photos, tracklist, teaser schedule

Output rules:
- List confirmed comeback date (or "目前無回歸消息")
- If new MV/song released this week → include YouTube link
- If comeback is announced but not yet released → show schedule/timeline

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 173)May include surrounding context.

md
- New song MV or audio on YouTube this week
- Concept photos, tracklist, teaser schedule

Output rules:
- List confirmed comeback date (or "目前無回歸消息")
- If new MV/song released this week → include YouTube link
- If comeback is announced but not yet released → show schedule/timeline

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 192)May include surrounding context.

md
- New song MV or audio on YouTube this week
- Concept photos, tracklist, teaser schedule

Output rules:
- List confirmed comeback date (or "目前無回歸消息")
- If new MV/song released this week → include YouTube link
- If comeback is announced but not yet released → show schedule/timeline

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
82% confidence
Finding

The skill instructs the agent to create and update local files (config.json and check_history.json) but does not declare any explicit tool scope or permissions boundary for file access. That mismatch can lead to overly broad or implicit filesystem capabilities, making unintended file writes harder to audit and constrain.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list is broad and includes generic entertainment terms, which can cause unintended invocation of a skill that reads and writes tracking files and may configure cron jobs. Accidental activation increases the chance of unanticipated persistence, external browsing, or scheduled tasks being set up in response to loosely related user requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file states that updates are summarized in Traditional Chinese, and later reinforces this with a rule to translate content to 繁體中文. This imposes a fixed language/locale choice without indicating user choice, opt-in, or a documented region-specific justification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill directs the agent to create and modify tracking files automatically if they do not exist, without an explicit warning or confirmation step. Silent file creation and modification are dangerous because they introduce persistent state changes and data retention that the user may not expect from a simple content-tracking request.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file contains substantial user-facing natural language in Chinese, including headings and feature descriptions, but does not indicate that the skill is intended only for Chinese-speaking users or that language is configurable. Under the policy rule for language/locale violations, forcing a specific language without opt-in can be a policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all headings and operational descriptions only in Traditional Chinese, with no opt-in, alternative language, or justification that the skill is limited to a Chinese-speaking audience.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.