Security audit

Social Selling Planner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed social-selling planning guide that produces human-executed workflows and avoids automation of platform actions.

Review whether you want bilingual Chinese/English wording in the skill’s outputs. The skill may save planning results and propose cadence records only after confirmation, so users should confirm saves only for information they want retained across sessions.

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The display name, summary, and description embed Chinese-language labeling alongside English, but the skill does not state that bilingual/Chinese output is optional or user-selected. This can violate a language/locale policy requiring user choice rather than imposing a specific language presentation by default.

Static analysis

No suspicious patterns detected.