Security audit

朋友圈文案

Security checks for vulnerabilities and agentic risk

Overview

This skill only guides the agent to write Chinese WeChat Moments captions from user-provided images or descriptions, without hidden code or privileged access.

This appears safe to install for generating WeChat Moments captions. Users should still be aware that implicit invocation is enabled, so the skill may be selected automatically for closely related caption-writing requests involving images, themes, or tone preferences.

SkillSpector

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 (2)

Vague Triggers

Medium

Confidence: 83% confidence
Finding: The default prompt invokes the skill with a generic phrase and does not encode clear activation boundaries beyond the natural-language description. In systems that support tool/skill routing, broad trigger wording can cause the skill to be selected in situations where the user did not specifically intend it, increasing the chance of inappropriate data use or unintended content generation.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: Enabling implicit invocation without narrowly defined activation conditions allows the platform to auto-select this skill based on loose semantic matches. That can lead to overbroad invocation, accidental processing of user-provided images or themes, and unexpected behavior in conversations that only partially resemble the intended use case.

Static analysis

No suspicious patterns detected.