ClawHub
Back to skill

Security audit

Daily Hot Push

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese trending-news digest with optional Feishu delivery, and its network use and scheduling are disclosed and aligned with that purpose.

Install this if you want a Chinese trending-news digest. If you enable the cron example, confirm the Feishu recipient ID and understand it will fetch public hot-list content and send the digest on the configured daily schedule until you remove that cron job.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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)

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The description states that the skill pushes '中国热榜TOP10' and the document consistently frames the skill as delivering China-specific trending news, but it does not provide opt-in language choice or explain why the locale restriction is required. The policy requires flagging language or locale constraints unless the user is offered a choice or the restriction is clearly documented and justified.

Missing User Warnings

Low
Confidence
92% confidence
Finding
The skill explicitly documents scheduled Feishu delivery, but it does not clearly warn users that enabling the cron workflow will automatically transmit collected news content to a Feishu account on a recurring basis. This is a real transparency and consent issue: users may configure the skill without fully appreciating the automatic outbound delivery behavior, which can cause unintended disclosures or surprise notifications, even though the content itself is news rather than highly sensitive data.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The manifest description is written entirely in Chinese and specifically states the skill pushes 'China hot list TOP10' from Chinese platforms, which indicates a China-specific language/locale scope without any mention of user choice or opt-in. Under the policy rules, locale constraints should be explicitly justified or optional rather than implicitly forced.

Static analysis

No suspicious patterns detected.