ClawHub
Back to skill

Security audit

wechat hot content

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly does what it claims, but its data-fetching script disables HTTPS verification, so reports and links could be tampered with in transit.

Review this skill before installing. It sends search keywords and dates to a third-party content-data API and writes local report files. Avoid using it for sensitive searches or on untrusted networks until the HTTPS verification issue is fixed, and consider whether displaying or exporting public-account metadata fits your compliance needs.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Context-Inappropriate Capability

High
Confidence
99% confidence
Finding
The custom HTTPS client disables certificate validation (CERT_NONE) and hostname checking, which removes TLS authentication and allows man-in-the-middle interception or tampering of API responses. Suppressing SNI further deviates from standard secure networking behavior and is not justified by the stated analytics use case, making remote data poisoning and misleading report generation feasible.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The document instructs the agent to fetch, aggregate, and display full public account article metadata, including account identifiers, QR-follow links, article URLs, and engagement metrics, but provides no warning about privacy, scraping, or platform Terms-of-Service constraints. In an agent context, these 'must query / must display everything' requirements can encourage unbounded collection and redistribution of third-party data, increasing compliance and misuse risk even if the data is partly public.

Static analysis

Detected: suspicious.insecure_tls_verification

HTTPS certificate verification is disabled.

Warn
Code
suspicious.insecure_tls_verification
Location
scripts/fetch_gzh_trends.py:132