TencentAds-miaowen-qa

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:18 PM UTC
• Version:
  1.0.2

Overview

This skill appears to be a disclosed Tencent Ads AI Q&A helper, but users should handle the Miaowen API token carefully.

Install only if you are comfortable using a Miaowen/Tencent Ads API key with this skill. Prefer configuring the token locally instead of pasting it into chat, avoid sending sensitive business or personal data in questions, and delete ~/.MIAOWEN_ACCESS_TOKEN or revoke the token when you no longer need it.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• 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 (5)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill instructs the agent to persist a user-provided access token to `~/.MIAOWEN_ACCESS_TOKEN` without an explicit up-front warning that the credential will be stored on disk. Storing secrets locally can expose them to other local processes, backups, shell-history mistakes, or later unintended reuse if the user did not knowingly consent to persistence.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The script transmits the user's free-form question to a third-party Tencent Ads API, but the UX only shows basic usage/help text and does not clearly warn users that their input will leave the local environment. This can lead users to unintentionally send sensitive business data, account details, or personal information to a remote service.

Ssd 3

Medium

• Confidence: 97% confidence
• Finding: The skill tells the user to paste their API token directly into the chat, creating a conversational credential-collection path. Chat channels may be logged, retained, reviewed, or exposed to other tools, so collecting secrets in natural language significantly increases the risk of credential disclosure and downstream account misuse.

Ssd 3

High

• Confidence: 99% confidence
• Finding: The script tells the user to paste their API token into the chat so it can be saved automatically. Encouraging secret submission through chat is dangerous because chat transcripts may be logged, retained, exposed to operators, or leaked to downstream systems, resulting in credential compromise.

Ssd 3

High

• Confidence: 99% confidence
• Finding: This repeats the same unsafe credential-handling pattern by asking the user to paste a newly obtained token for re-saving. Repetition increases the likelihood of secret disclosure and normalizes unsafe handling of credentials within conversational channels.

VirusTotal

65/65 vendors flagged this skill as clean.