Back to skill

Security audit

Blackboard

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward blackboard-poster image generation skill with minor clarity issues, not evidence of unsafe or malicious behavior.

Install this skill if you want a Chinese blackboard-style vertical poster generator. Avoid using confidential campaign details unless you are comfortable with the generated image and full prompt being returned through Feishu, and be aware it may trigger on broad poster requests.

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
95% confidence
Finding

The trigger phrases are broad enough to match many ordinary image-generation or design requests, which can cause this skill to activate unexpectedly instead of a more appropriate tool or safer workflow. Because the skill automatically generates images and later instructs sending outputs and prompts via Feishu, over-triggering increases the chance of unintended data handling and user confusion about where their content is being sent.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The '字体风格' section includes 'handwritten style Chinese text' as an endorsed font direction, while later the comparison table states that blackboard style uses '现代印刷风'. These documentation statements describe incompatible design intent, creating active divergence within the skill's guidance about what the output should look like.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Line L46 says '不要写中文在提示词里' and directs users to use English descriptions instead. This is a natural-language locale policy issue because it imposes a language constraint without offering opt-in, alternatives, or a documented regional/compliance reason.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest says this skill's hallmark is '手写马克笔字体风格' with thick, irregular marker strokes, but the guide's blackboard-style comparison explicitly describes the text as '现代印刷风'. This is a semantic mismatch in the skill's own documented behavior and could cause the skill to generate outputs inconsistent with its stated purpose.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill directs the agent to send the generated image and full prompt text via Feishu, but the user-facing description does not clearly warn that their content will be transmitted through that channel. This creates a transparency and privacy issue: users may provide sensitive brand, campaign, or proprietary prompt details without realizing those details will be shared externally.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file presents the skill content in a fixed bilingual format: section titles and placeholders are in Chinese while the template instructions are in English. Under the policy rule, forcing a specific language or locale without user opt-in can be a natural-language policy issue, and the file does not state that it is intentionally region-specific or offer alternatives.

Content

No source excerpt is available for this finding.