ClawHub
Back to skill

Security audit

Reviewcourt

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent Tencent Meeting review assistant that discloses its CLI/OAuth use and does not contain hidden scripts or unrelated data actions.

Install only if you are comfortable granting the Tencent Meeting CLI access to ended meeting records and transcripts for review. Confirm any CLI installation and OAuth login yourself, and use it only for meetings and PRD files you are authorized to analyze.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
The document title and the throughout instructions are written as binding output guidance in Chinese, including stylistic constraints and required phrasing, but there is no indication that users may choose another language. This can violate a language/locale policy when a skill forces a specific language without user opt-in or documented region-specific justification.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.