Back to skill

Security audit

domain-knowledge-system

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed learning-workflow skill that may scan public information sources and suggest recurring learning follow-ups, with no hidden code, credential use, or destructive behavior found.

Install this if you want a Chinese-language structured learning workflow. Before using its weekly or monthly tracking suggestions, confirm that you actually want recurring agent follow-ups and review any recommended sources before following them.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The README is entirely written in Chinese and all invocation examples are Chinese, but there is no statement that the skill supports other languages or that Chinese-only behavior is intentional and justified. Under the policy, a language constraint should either be optional for the user or explicitly documented as a justified locale-specific limitation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The invocation description is broad enough that an agent could trigger this skill for many loosely related requests about learning or understanding a topic, increasing the chance of unintended activation. In this skill’s context, unintended activation matters because the skill initiates multi-step scanning and tracking behavior, which can cause over-collection of external content, user confusion, or execution of a workflow the user did not explicitly request.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger conditions are broad enough to match ordinary learning or exploratory requests, which can cause the skill to activate unexpectedly. In this skill's context, unintended activation matters because it can initiate external-source scanning, produce persistent tracking plans, and steer the conversation into a predefined workflow without clear user consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill describes scanning external platforms and setting up ongoing weekly/monthly tracking outputs, but it does not warn the user up front that this workflow may monitor third-party sources and create recurring follow-up artifacts. That lack of transparency can lead to consent and privacy issues, especially if users do not expect persistent tracking or external-source monitoring from a simple 'intro to a field' request.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The description is written as a Chinese-only invocation and usage experience, with no indication that users may choose another language or locale. Under the policy, a fixed language without opt-in can be a natural-language policy issue unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.