Back to skill

Security audit

Kubernetes 301363

Security checks for vulnerabilities and agentic risk

Overview

This is a Kubernetes study-note skill with no executable behavior, but its broad triggers and duplicated Chinese content may make it activate unexpectedly or feel low quality.

Install only if you want a Chinese-language Kubernetes learning helper. Expect possible accidental activation on generic Kubernetes questions unless the trigger wording is narrowed by the publisher.

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 (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The description and surrounding instructional content are presented in Chinese, but the file does not indicate that the user opted into Chinese or that the skill is intentionally restricted to a Chinese-speaking context. This can violate language/locale policy when a skill implicitly forces one language without user choice.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest trigger contains generic Kubernetes-related wording and promotional phrases without clear activation constraints, making accidental activation likely for unrelated or general Kubernetes conversations. Ambiguous manifest triggers increase collision risk with other skills and reduce user control over which skill is selected.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger conditions include very broad phrases such as users saying 'Kubernetes' or requesting Kubernetes-related help, which can cause the skill to activate during ordinary platform usage rather than only when explicitly invoked. This creates unintended routing/selection behavior and can expose users to irrelevant or low-quality guidance from this merged skill content.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This duplicated trigger section repeats vague activation rules such as broad skill-name or topic-based invocation, which compounds the chance of accidental activation and increases routing ambiguity. Repetition across merged content suggests the skill was auto-assembled without normalization, making trigger conflicts more likely.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This additional duplicated trigger block again uses unspecific invocation language, preserving the same accidental activation problem even if earlier sections are corrected. Multiple broad trigger blocks can cause maintenance errors and inconsistent downstream enforcement of activation rules.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The final trigger block still includes generic Kubernetes support phrasing, which is likely to collide with normal user requests and unintentionally invoke this skill. Although the content appears educational, generic activators can still degrade routing integrity and user trust.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.