Security audit

Feishu Screenshot

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says, but it can capture the whole screen and send it to Feishu from very broad screenshot requests without a clear confirmation step.

Install only if you are comfortable with a skill that may capture everything visible on the primary screen and send it to Feishu. Prefer using it only after closing or hiding sensitive windows, and the skill should ideally require explicit Feishu/send intent plus a preview or confirmation before transmission.

A.I.G

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

SkillSpector

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 (2)

Missing User Warnings

High

Confidence: 98% confidence
Finding: The skill captures the entire primary screen and sends the resulting file to Feishu, but the description and workflow do not present a clear user-facing warning or consent checkpoint about full-screen data capture and exfiltration. This is especially risky because screenshots may contain passwords, confidential documents, chats, tokens, or personal information visible anywhere on the screen at the time of capture.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger phrases include very common terms like “截图” and “屏幕截图”, which can easily match routine user requests without clearly indicating that the image will be sent to Feishu. In this skill’s context, accidental invocation is dangerous because it performs a full-screen capture and initiates transmission of potentially sensitive on-screen data to an external messaging platform.

Static analysis

No suspicious patterns detected.