Security audit

AI News Aggregator

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only news aggregation skill with some broader finance-news templates, but it does not install code, collect credentials, persist, or take high-impact actions by itself.

Install only if you want a Chinese-oriented AI/tech news reference skill that also includes finance-news summarization templates. Treat any market-impact or sentiment-risk output as informational, verify sources manually, and do not rely on it for investment decisions.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Intent-Code Divergence

Medium

Confidence: 92% confidence
Finding: The top-level documentation narrows use to AI/tech news, yet later content instructs generation of finance briefings and market-impact analysis. This inconsistency undermines trust boundaries: agents may activate or approve the skill under a low-risk news label while actually being guided into financial-content generation, where errors or overreach can cause greater harm.

Description-Behavior Mismatch

Medium

Confidence: 95% confidence
Finding: The skill is presented as an AI/tech news aggregator, but a large appendix materially expands it into finance-news workflows, market-impact summaries, sentiment/risk warnings, and finance-specific output templates. That scope drift can mislead downstream agents or users into applying the skill in higher-risk financial contexts without explicit reclassification, stronger safeguards, or domain-specific controls.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: This markdown file contains natural-language instructions and templates that explicitly require English news to be translated into Chinese and expect Chinese-language output structure. Because the skill does not offer opt-in language selection or clearly justify a Chinese-only locale scope, it conflicts with the language/locale policy requirement.

Static analysis

No suspicious patterns detected.