Back to skill

Security audit

Daily Tech Brief

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only briefing skill that tells the agent how to gather and format a daily technology news summary, with no hidden code or persistence found.

Installers should expect this skill to perform current web/news research and use the ClawHub CLI for ClawHub-related items. If it is used from cron or automation, review the caller-specified podcast or briefing script separately before allowing execution.

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
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

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The instruction "默认中文输出" imposes a language preference in the skill's natural-language behavior. The policy allows locale constraints only when the user is given a choice or when the restriction is clearly justified as region-specific, which is not stated here.

Content

No source excerpt is available for this finding.