Cn Social Reply

• Outcome: Pass
• Latest audit: Jun 7, 2026 at 3:54 AM UTC
• Version:
  1.2.7

Overview

This skill is a disclosed social-media reply helper with a small local style-template manager and no evidence of hidden network, credential, or destructive behavior.

Install only if you are comfortable storing reply-style preferences locally in ~/.qclaw/workspace/cn-social-reply/styles.json. Avoid putting sensitive personal, brand, or account details into saved style templates unless you want them retained on disk.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Low

• Confidence: 84% confidence
• Finding: The skill instructs the agent to save, load, and delete user style templates from a persistent local JSON file, but it does not clearly warn users that their preferences will be stored on disk or removed permanently. This can create privacy and surprise risks, especially if style templates contain personal branding details, behavioral preferences, or other sensitive metadata the user did not expect to persist.

VirusTotal

65/65 vendors flagged this skill as clean.