ClawHub
Back to skill

Security audit

Daily Insight Brief

Security checks for vulnerabilities and agentic risk

Overview

This is a benign Chinese daily briefing skill that gathers public information sources and formats a news/business brief, with no executable code or hidden persistence found.

Install this if you want a Chinese-language daily brief built from public business, technology, finance, and media sources. Before enabling any real scheduler or Feishu/email/channel delivery, confirm the destinations, credentials, and opt-in controls so reports are not sent somewhere unexpected.

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
  • 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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill states it will automatically fetch and aggregate information from many external sources and may later write outputs to Feishu documents, email, or channels, but it does not clearly warn users about this behavior up front. This can lead to unexpected network access, third-party data sharing, or content publication without informed user consent, especially in environments where outbound actions are sensitive.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 85)May include surrounding context.

md
---

如果你愿意，我可以直接把这份草案落在 /Users/alex/.openclaw/workspace/skills/daily-insight-brief/SKILL.md，并继续为你生成第一版3-5条样例 Brief，以及初步的来源候选扩展清单。请确认是否直接使用以上草案文本，或你希望对描述、字段或格式做进一步定制。

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file’s instructional content is written entirely in Chinese and does not indicate that language selection is optional or user-configurable. Under the policy rule for natural-language violations, forcing a specific language without opt-in can be a locale/language policy issue unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill specifies Chinese as the primary output language without indicating that this is configurable or requires user preference. While not a direct security flaw, it can cause usability and transparency issues, especially if users rely on the output for review, verification, or downstream automation in another language.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.