ClawHub
Back to skill

Security audit

Tech Morning Briefing

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed daily tech-news briefing skill that posts to Feishu and keeps local state, with no evidence of hidden or unrelated behavior.

Install only if you want an automated daily workflow that can search the web, post to Feishu, append to a Feishu document, and store local runtime files. Confirm the Feishu chat/document destination and permissions before enabling the cron job, and keep data/config.json private because it stores the Feishu document token.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The README explicitly states that the skill will push messages to Feishu and append content to a Feishu document, but it does not clearly warn users that installing or scheduling the skill causes writes to external third-party resources. In an agent context, silent outbound side effects are security-relevant because users may grant Feishu permissions without understanding that chats and documents will be modified automatically on a recurring basis.

Missing User Warnings

Low
Confidence
94% confidence
Finding
The skill explicitly writes and updates persistent local files such as `data/news-pool.json`, `data/config.json`, and `data/quotes-used.json` but does not tell the user that local state will be created and retained across runs. This is risky because users may not realize the skill stores history, configuration, and potentially sensitive operational metadata on disk, which can affect privacy, reproducibility, and cleanup expectations.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill automatically creates and appends to a Feishu document and instructs passing `owner_open_id`, causing content to be transmitted to an external service without an explicit user consent or warning in the skill itself. This is more dangerous in context because the collected news summaries, archives, and account-linked document metadata are synchronized off-platform on a scheduled basis, creating ongoing external data exposure.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.