ClawHub
Back to skill

Security audit

news-daily

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says, but it weakens HTTPS security while handling a Feishu webhook, so users should review or patch it before installing.

Install only after accepting or fixing the transport-security risk. Remove the disabled TLS verification, keep the Feishu webhook in a protected environment variable or secret store, avoid committing config.json, and enable cron or hooks only if you want automatic recurring posts.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill documentation shows capabilities to read environment/configuration, access local files, and perform outbound network requests, yet it declares no permissions. This creates a transparency and consent gap: operators may install or schedule the skill without realizing it can read secrets and transmit data externally, which is especially relevant because it uses a Feishu webhook and RSS fetching.

Intent-Code Divergence

Medium
Confidence
99% confidence
Finding
The script globally disables TLS certificate validation by setting check_hostname=False and verify_mode=ssl.CERT_NONE, then reuses that context for both RSS fetches and Feishu webhook delivery. This makes HTTPS connections vulnerable to man-in-the-middle interception or tampering, allowing an attacker on the network path to inject malicious feed content, steal the webhook destination traffic, or alter outbound requests/responses.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill explicitly fetches content from RSS sources and sends formatted results to a Feishu webhook, but the documentation does not clearly warn users that it performs outbound network transmission to third-party services. This can lead to unintentional data egress and weak informed consent, especially when the skill is configured to run automatically.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The instructions ask users to place the Feishu webhook in an environment variable or config file, but do not state that the webhook URL is effectively a secret that can be abused to post messages into the target chat if leaked. This raises the risk of credential mishandling, accidental commits, and unauthorized message injection.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal