Back to skill

Security audit

knowledge-capture

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local knowledge-capture and study-tracking helper whose persistence is disclosed and aligned with its stated purpose.

Install this if you want a Chinese-language local study notebook that saves conversation-derived notes and tracks quiz performance over time. Be mindful that saved notes, scores, weak points, and review history may contain sensitive personal or work information, so review or delete the files if you do not want that learning profile retained.

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 (4)

Vague Triggers

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad, common conversational expressions, so the skill may activate during ordinary dialogue without clear intent to persist data. In this skill, activation leads to writing structured notes, updating question banks, and tracking mastery state on disk, which creates a real risk of unintended data retention and profile creation from casual user speech.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The scoring-update trigger is ambiguous because any reply that looks like an answer to a question could be interpreted as consent to grade and update persistent mastery records. That can cause silent modification of learning history and behavioral profiling even when the user is only continuing the conversation rather than participating in a review workflow.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill performs persistent writes to notes, question-bank.json, mastery-status.json, and a review schedule, but it does not require an explicit warning that user content and performance data will be stored and used for ongoing profiling. Because the skill tracks weak points, scores, and review history over time, omission of disclosure undermines informed consent and increases privacy risk if sensitive conversations are captured.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The template’s headings and instructional text are entirely in Chinese, which imposes a specific language on users without offering an opt-in or alternative locale. Under the policy criteria, fixed language requirements are acceptable only when user choice is offered or the locale restriction is clearly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.