Back to skill

Security audit

AI Weekly Report

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese AI news weekly-report generator that fetches from listed sources and may save a Markdown report file.

Install only if you want a Chinese-language AI news report skill. When invoked, expect it to access the listed news sites and, where file operations are available, create a Markdown report in the current working directory using the requested date range.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructs the agent to write a Markdown file into the current directory without requiring explicit user confirmation at write time or warning that a filesystem side effect will occur. In agent environments, silent file creation can surprise users, overwrite expected workspace state, or be chained with other behaviors to persist sensitive or misleading content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The name/description and operating instructions are entirely in Chinese and present the skill as producing a Chinese-language weekly report, but there is no user opt-in or stated reason for restricting language/locale behavior. This can conflict with policy requiring language choice unless the locale limitation is explicitly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.