Back to skill

Security audit

Whiteboard Prompt Crafter

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent whiteboard image-prompt skill with ordinary image generation behavior, though users should know it may create files and send generated outputs through Feishu.

Install this if you want Chinese-oriented whiteboard illustration prompts and image generation. Review prompts before generation when working with confidential ideas, because the workflow sends content to an image generation tool and then posts the generated image and prompt through Feishu.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are broad enough that normal user requests about making a whiteboard illustration or asking how to achieve a style could invoke the skill unintentionally. Because the skill can then generate files and proceed to downstream actions, accidental invocation can cause unexpected processing and outputs the user did not explicitly request.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill specifies writing generated files to workspace storage and sending them via a messaging channel, but the description does not clearly warn users that content may be transmitted externally. If users provide sensitive business concepts, private images, or confidential prompts, those outputs could be shared beyond the immediate chat context without informed consent.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest says generated images should contain only the whiteboard itself, with no background and the whiteboard filling the frame. However, this reference guide instructs prompts to always include 'whiteboard on wall', 'warm fluorescent lighting', and an 'office background slightly blurred', which expands output beyond a background-free whiteboard image.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
73% confidence
Finding

The natural-language instructions are written to operate around Chinese titles, Chinese text labels, and Chinese trigger phrases, but do not indicate that users may choose another language. This can be a language/locale policy issue when a skill effectively assumes one language without opt-in or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file presents its instructions entirely in Chinese, which can amount to a language/locale restriction if users are expected to consume it as part of the skill. The policy requires either offering a language choice or clearly documenting and justifying the locale constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file is a prompt template library whose headings and multiple template placeholders explicitly require Chinese text, such as 'Hand-drawn style Chinese text' and Chinese-only title/label placeholders. This imposes a specific language choice throughout the skill content without documenting user opt-in or a justified locale-specific constraint.

Content

No source excerpt is available for this finding.