Daily Antifraud Report

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:24 PM UTC
• Version:
  1.0.0

Overview

This skill coherently generates a Chinese anti-fraud news briefing, but users should configure its scheduled run and Feishu posting deliberately.

Install only if you want a daily anti-fraud news report workflow. Before enabling it, confirm the cron schedule, use a narrowly scoped Feishu webhook or destination, and avoid putting internal incident details, customer data, secrets, or sensitive monitoring interests into search queries.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• 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

Findings (3)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 88% confidence
• Finding: The skill claims a narrowly scoped purpose but its described behavior is broad, underspecified, and lacks constraints enforcing Chinese domestic anti-fraud sources or exclusion of foreign institutions. This mismatch can cause the agent to gather irrelevant or untrusted information, expand beyond intended scope, and produce misleading reports that may be acted on or redistributed.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The workflow says the compiled report will be pushed to Feishu, but it provides no user notice, confirmation step, or data-handling boundary before transmitting gathered content to an external service. If the report contains sensitive incident details, internal notes, or inaccurate scraped content, this creates data leakage and unintended dissemination risk.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The script sends the user-supplied search query directly to Baidu over the network, which discloses potentially sensitive operational queries to a third party without any notice, consent flow, or data-minimization controls. In this skill's context, the query is about anti-fraud reporting for domestic banks and payment institutions, so searches may reveal monitoring interests, internal investigative topics, or scheduled reporting subjects.

VirusTotal

66/66 vendors flagged this skill as clean.